© 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. 127309
    Prev
    Next
    INDEX
    Explanations

    Divine Call; Wars are Lost

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

    common or specific terms

    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
    ᅬ
    0.49
    ινή
    0.46
     rejuvenated
    0.46
    ವಾಡ
    0.45
     bewildered
    0.44
    ین
    0.44
    ου
    0.43
    降り
    0.43
    ι
    0.43
    行走
    0.42
    POSITIVE LOGITS
    ~
    0.50
    ্দ
    0.49
    TK
    0.49
     área
    0.48
     قائ
    0.47
    Mult
    0.46
    )
    0.46
    textcolor
    0.46
    etak
    0.46
    yo
    0.46
    Activations Density 0.000%

    No Known Activations