© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39997
    Prev
    Next
    INDEX
    Explanations

    instructions or specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Corv
    0.53
    ﻠ
    0.52
    たち
    0.48
    ља
    0.48
    労
    0.48
    찝
    0.47
     моби
    0.47
     prestataire
    0.47
    邃
    0.46
    ÊN
    0.45
    POSITIVE LOGITS
     (
    0.51
     consec
    0.48
     sin
    0.44
     experiment
    0.42
     orchestra
    0.42
     arm
    0.41
    G
    0.41
     insign
    0.41
     studie
    0.41
     incident
    0.41
    Activations Density 0.000%

    No Known Activations