© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19652
    Prev
    Next
    INDEX
    Explanations

    credit schedule

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

    field definition or attribute

    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
    सायिक
    0.52
    〝
    0.52
    Cemento
    0.51
    remeno
    0.50
    िद
    0.49
    ﻛ
    0.49
    ազ
    0.46
    usually
    0.46
    <0xEC>
    0.45
    rado
    0.44
    POSITIVE LOGITS
     frivol
    0.50
     exclusivity
    0.50
    參加
    0.47
     any
    0.45
     formée
    0.44
     slits
    0.44
     bunting
    0.43
     `>=
    0.43
     بام
    0.43
     Darmstadt
    0.42
    Activations Density 0.000%

    No Known Activations