© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105848
    Prev
    Next
    INDEX
    Explanations

    movie and crime dramas

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on mentions of specific media titles or proper‐named entertainment works (e.g. film, book, series, magazine titles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dinosaurio
    -1.38
     únicos
    -1.20
    鲥
    -1.18
     personnalisées
    -1.09
     involucrados
    -1.09
     Mereka
    -1.09
     única
    -1.09
     detenidos
    -1.08
    fabricated
    -1.08
     your
    -1.07
    POSITIVE LOGITS
     gestartet
    1.15
    ellites
    1.13
     he
    1.13
    gebiet
    1.09
     pubblicato
    1.05
     onPostExecute
    1.05
     Such
    1.04
     considerazione
    1.04
     hooked
    1.03
    crição
    1.03
    Activations Density 0.039%

    No Known Activations