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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102521
    Prev
    Next
    INDEX
    Explanations

    movie titles or characters

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

    The neuron fires on named entities—especially capitalized proper names and titles (e.g. movie/series titles, character names, people, brands).

    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
    '
    -1.63
     влади
    -1.39
    もちゃ
    -1.38
     arī
    -1.37
     '
    -1.36
    ＆
    -1.32
    -"
    -1.30
    isation
    -1.29
    </strong>
    -1.27
    VIATIONS
    -1.27
    POSITIVE LOGITS
    нование
    1.53
    泐
    1.52
     like
    1.46
     sobri
    1.45
    暃
    1.45
    ”.
    1.40
     ہوا
    1.31
     höchsten
    1.31
    valier
    1.30
    VIOUS
    1.28
    Activations Density 0.043%

    No Known Activations