© 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. 41703
    Prev
    Next
    INDEX
    Explanations

    GET requests for data

    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
    Pending
    0.41
    q
    0.40
    ίνη
    0.39
    ()).
    0.39
    nd
    0.38
    ();
    0.38
    ৯
    0.38
    dagger
    0.38
    zIndex
    0.38
    illiant
    0.37
    POSITIVE LOGITS
     STRAIGHT
    0.40
     multiplicar
    0.39
     STUDY
    0.39
     Madagascar
    0.38
     →
    0.37
     stimulates
    0.37
     $/
    0.37
     percentage
    0.37
     percentages
    0.36
     когато
    0.36
    Activations Density 0.015%

    No Known Activations