© 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. 14555
    Prev
    Next
    INDEX
    Explanations

    weather map

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

    performance degradation and states

    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
    ávat
    0.45
    "
    0.45
     nominally
    0.45
    "#
    0.44
    विड
    0.44
    可通过
    0.44
    וף
    0.44
    無
    0.44
    í
    0.44
    kov
    0.43
    POSITIVE LOGITS
     이걸
    0.54
     AEG
    0.54
     reimb
    0.52
     লোককে
    0.51
     인수
    0.50
    솎
    0.50
     இருந்தால்
    0.50
     Paise
    0.50
     કાર્ડ
    0.49
     अभिषेक
    0.49
    Activations Density 0.000%

    No Known Activations