© 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. 153676
    Prev
    Next
    INDEX
    Explanations

    don't forget

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

    NPC behavior, TikTok, colleague, cameras, smiles

    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
    變
    0.52
    雖然
    0.47
    蒾
    0.47
     (=
    0.46
    っていない
    0.46
    (=
    0.45
    ထ
    0.45
    訓練
    0.45
    훈련
    0.44
    ฝึก
    0.44
    POSITIVE LOGITS
     Davey
    0.50
     подробно
    0.49
    jane
    0.48
    лили
    0.48
    ude
    0.48
     আর্কাইভ
    0.48
     rumores
    0.47
    ang
    0.47
     jueves
    0.46
     విధంగా
    0.46
    Activations Density 0.001%

    No Known Activations