© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46928
    Prev
    Next
    INDEX
    Explanations

    newsletters published

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

    AI models and predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ρι
    0.56
    粦
    0.55
     диф
    0.51
    يل
    0.51
    ళ
    0.51
    రం
    0.50
    )、
    0.50
    桕
    0.50
     ተመሳሳይ
    0.49
    ساوي
    0.48
    POSITIVE LOGITS
     newsletters
    0.50
     liabilities
    0.49
    y
    0.49
    </td>
    0.48
     turnovers
    0.48
     wishes
    0.47
     tournaments
    0.46
     will
    0.46
     stresses
    0.46
    </strong>
    0.46
    Activations Density 0.000%

    No Known Activations