© 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. 48907
    Prev
    Next
    INDEX
    Explanations

    installation or update success

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

    advantages and offers

    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
    AL
    0.51
    per
    0.50
    and
    0.50
    Z
    0.49
    cę
    0.48
    rado
    0.47
    Pho
    0.47
    planner
    0.47
    ON
    0.46
    /
    0.46
    POSITIVE LOGITS
     বিদ্রোহী
    0.48
     Rebel
    0.47
     ölüm
    0.46
     বিক্ষোভ
    0.46
    ージュ
    0.45
     জামাল
    0.45
    }}:=\
    0.45
     বিজনেস
    0.44
     রুশ
    0.44
     নায়ক
    0.43
    Activations Density 0.001%

    No Known Activations