© 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. 26004
    Prev
    Next
    INDEX
    Explanations

    code closing punctuation

    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
     нужно
    -1.02
     leaft
    -0.97
     holocaust
    -0.94
     voodoo
    -0.94
     berühm
    -0.94
    Ār
    -0.93
    UVW
    -0.93
     personaggio
    -0.91
    otras
    -0.91
     akhirnya
    -0.91
    POSITIVE LOGITS
     and
    1.02
    </tbody>
    0.97
    What
    0.97
    :}
    0.95
    Who
    0.90
    !
    0.90
    Because
    0.88
    egrave
    0.88
    <eos>
    0.88
     együtt
    0.88
    Activations Density 0.005%

    No Known Activations