© 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. 209886
    Prev
    Next
    INDEX
    Explanations

    runways for, full warranty, blood borne

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

    astrology, cricket, conversation, computing, pages, beaches

    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
     নিযুক্ত
    0.48
     Agents
    0.46
     निरीक्षक
    0.46
    Agents
    0.45
    Ple
    0.45
    <unused979>
    0.45
    agents
    0.44
     本当
    0.43
     뭐야
    0.43
     tm
    0.43
    POSITIVE LOGITS
    αρ
    0.44
     asymmetry
    0.43
    biased
    0.43
    fancy
    0.43
    論文
    0.43
     υψη
    0.42
     kB
    0.42
    :<
    0.42
    Dress
    0.42
    鞄
    0.42
    Activations Density 0.000%

    No Known Activations