© 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. 34-GEMMASCOPE-RES-131K
    7. 12079
    Prev
    Next
    INDEX
    Explanations

    key selling points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    gebühren
    -0.96
    δυ
    -0.90
    lético
    -0.87
    legte
    -0.87
    дії
    -0.84
    эффек
    -0.84
     resultat
    -0.81
    aisons
    -0.81
    </tfoot>
    -0.80
    írit
    -0.80
    POSITIVE LOGITS
     selling
    3.63
    Selling
    2.77
     Selling
    2.66
    selling
    2.42
     attraction
    2.22
     sell
    2.11
     USP
    2.09
    卖
    2.08
     appeal
    2.06
     distinguishing
    1.94
    Activations Density 0.047%

    No Known Activations