© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66257
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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_22/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
    )&&(
    -0.98
    ですし
    -0.97
     trató
    -0.96
    食感
    -0.95
    ggere
    -0.90
    oxone
    -0.89
    //};
    -0.88
     téc
    -0.86
     tieto
    -0.86
     Enquanto
    -0.85
    POSITIVE LOGITS
     休闲
    1.00
     nedan
    0.94
    ANG
    0.93
    GREATER
    0.92
     their
    0.86
    gypten
    0.85
    醚
    0.84
    kében
    0.83
    ENR
    0.82
    KING
    0.82
    Activations Density 0.002%

    No Known Activations