© 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. 28340
    Prev
    Next
    INDEX
    Explanations

    why coordinate or fair value

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

    Elizabeth Trump & Son

    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
    ༩
    0.49
     promulgated
    0.48
     ശിവ
    0.48
     prawie
    0.48
    ന്ദ
    0.47
     pesquis
    0.47
     funkci
    0.46
    যত
    0.45
    鳇
    0.45
     splendor
    0.45
    POSITIVE LOGITS
    geno
    0.50
    ermont
    0.49
    omo
    0.49
    ો
    0.49
    )$;
    0.47
    erman
    0.46
    ammo
    0.46
    auri
    0.46
    erm
    0.46
    েল
    0.46
    Activations Density 0.000%

    No Known Activations