© 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. 34-GEMMASCOPE-RES-131K
    7. 3209
    Prev
    Next
    INDEX
    Explanations

    abstract texts

    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
    !
    -1.20
     :)
    -1.06
    &#
    -1.05
    !"
    -0.98
     &
    -0.98
     crazy
    -0.95
     !
    -0.93
    !”
    -0.90
     TikTok
    -0.90
     from
    -0.90
    POSITIVE LOGITS
     ᾿
    0.97
     Boi
    0.96
     metà
    0.93
     aggres
    0.92
     precious
    0.90
    -),
    0.90
    precious
    0.88
    ține
    0.87
    ???????
    0.87
    ?—
    0.87
    Activations Density 0.013%

    No Known Activations