© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113061
    Prev
    Next
    INDEX
    Explanations

    control back

    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
    Ｌ
    0.44
    Ű
    0.42
    ABD
    0.42
    apeake
    0.41
    ﻁ
    0.41
     Chandra
    0.40
    ighton
    0.40
    ing
    0.40
    ITY
    0.40
    üman
    0.39
    POSITIVE LOGITS
     permettant
    0.43
     concernant
    0.43
     apprend
    0.42
     واح
    0.42
     jsou
    0.40
     मूर्
    0.39
     рассмотре
    0.38
    讽
    0.38
     التن
    0.38
     수업
    0.38
    Activations Density 0.002%

    No Known Activations