© 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. 194493
    Prev
    Next
    INDEX
    Explanations

    kind of

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

    change, states, categories

    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
     subgoal
    0.51
    ციის
    0.50
     skier
    0.48
    一项
    0.47
    覷
    0.46
     glucos
    0.45
     Yorker
    0.45
    Xi
    0.44
     xanth
    0.44
    ্ডিং
    0.44
    POSITIVE LOGITS
    ાર્
    0.45
    忽
    0.44
    enas
    0.42
    臨
    0.41
     أول
    0.41
    éristique
    0.41
    ̀
    0.41
    ライブ
    0.40
    РО
    0.40
    改
    0.40
    Activations Density 0.000%

    No Known Activations