© 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. 127389
    Prev
    Next
    INDEX
    Explanations

    free download

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

    The neuron flags promotional calls to action offering free downloads (e.g. “Free Download,” “full version,” etc.).

    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
    breos
    -1.28
     cliente
    -1.20
     zodat
    -1.19
     violeta
    -1.18
     escalier
    -1.17
     którzy
    -1.16
     it
    -1.16
     dimanche
    -1.15
    </strong>
    -1.14
    wnicy
    -1.14
    POSITIVE LOGITS
     żad
    1.19
     tampoco
    1.17
    cluding
    1.16
     カジュアル
    1.14
     dispoz
    1.14
     fapt
    1.14
    except
    1.13
     funzionalità
    1.13
     ポーチ
    1.13
     piú
    1.13
    Activations Density 0.077%

    No Known Activations