© 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. 42625
    Prev
    Next
    INDEX
    Explanations

    specific details preceding dates or events

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

    focuses on, tries to, worried about

    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
    0
    0.55
    (
    0.54
    "
    0.53
    mine
    0.47
    erm
    0.44
    ع
    0.44
    8
    0.44
    ari
    0.42
    li
    0.42
    Fire
    0.41
    POSITIVE LOGITS
    <unused2173>
    0.58
     遊ん
    0.57
     adhipp
    0.55
     考え
    0.54
     شرطونو
    0.54
    सीएस
    0.54
     亻
    0.54
     Kxg
    0.53
     LOCCTR
    0.53
     入っ
    0.53
    Activations Density 0.000%

    No Known Activations