© 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. 62681
    Prev
    Next
    INDEX
    Explanations

    celebrated additions, contemplating filing, work things

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

    defining state or action

    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
     Aug
    0.47
     Eight
    0.46
     ငါ
    0.46
     मगर
    0.44
     ମ
    0.43
     not
    0.43
     Kegiatan
    0.42
    傍
    0.42
     Nine
    0.42
     CLAIM
    0.42
    POSITIVE LOGITS
    暂时
    0.50
    RenderTarget
    0.49
    PointSize
    0.45
     மேற்பட்ட
    0.44
    மில்
    0.43
    Sprite
    0.43
    மி
    0.41
    צב
    0.41
    }-
    0.41
    Shard
    0.41
    Activations Density 0.000%

    No Known Activations