© 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. 113377
    Prev
    Next
    INDEX
    Explanations

    author names

    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
     automorphism
    0.46
     Sponsor
    0.45
     Donations
    0.45
     admin
    0.44
    特殊
    0.43
    య
    0.43
    abouts
    0.43
     special
    0.43
     auth
    0.43
     khusus
    0.42
    POSITIVE LOGITS
    urt
    0.46
     trecut
    0.44
    ód
    0.41
    ade
    0.41
    lose
    0.41
    ]<?
    0.41
    ill
    0.40
     tolle
    0.39
    ram
    0.39
    ly
    0.39
    Activations Density 0.000%

    No Known Activations