© 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. 40-GEMMASCOPE-2-RES-262K
    7. 210476
    Prev
    Next
    INDEX
    Explanations

    public interest, research, and criteria

    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_40_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
     인생
    0.42
    তন
    0.39
     LOTRAchievement
    0.38
    たっぷり
    0.37
    鐩
    0.37
    ைத்
    0.37
     equivalently
    0.37
    তনে
    0.37
    琹
    0.37
    广泛
    0.36
    POSITIVE LOGITS
    ublic
    0.42
     sa
    0.40
    Vault
    0.40
     Mighty
    0.40
     public
    0.40
     files
    0.40
     CHILDREN
    0.39
    Public
    0.38
     trucks
    0.38
     criteria
    0.38
    Activations Density 0.000%

    No Known Activations