© 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. 41216
    Prev
    Next
    INDEX
    Explanations

    legal or required actions

    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
    Indent
    0.40
     SKAction
    0.39
    BO
    0.39
    Bollywood
    0.39
    Smith
    0.38
    There
    0.38
    Nit
    0.38
    ​.
    0.38
     төр
    0.38
    t
    0.38
    POSITIVE LOGITS
     uneasy
    0.55
     duality
    0.53
     keenly
    0.51
     garantie
    0.46
     garantizar
    0.46
     assurances
    0.46
     specular
    0.45
     indeed
    0.45
     carcinogenic
    0.45
     vicar
    0.44
    Activations Density 0.004%

    No Known Activations