© 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. 22067
    Prev
    Next
    INDEX
    Explanations

    group programs

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

    liquidity pools, careful questions, glad to help

    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
     건축
    0.49
     현대
    0.46
     很
    0.45
     รอ
    0.45
     Моск
    0.45
     확장
    0.45
     거
    0.44
    URNIZOR
    0.44
    }}
    0.43
    ITwitter
    0.43
    POSITIVE LOGITS
    ાદ
    0.46
    m
    0.46
    Dto
    0.46
     mile
    0.45
     on
    0.45
     prints
    0.45
     sea
    0.44
    товой
    0.44
     printer
    0.44
    kill
    0.44
    Activations Density 0.000%

    No Known Activations