© 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. 108611
    Prev
    Next
    INDEX
    Explanations

    acknowledging and refusing harmful requests

    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
     ليست
    0.46
    şe
    0.45
     മിക
    0.45
    şa
    0.44
     ކ
    0.43
    asserie
    0.42
    ický
    0.42
     lakini
    0.42
    indi
    0.41
    agh
    0.41
    POSITIVE LOGITS
     datos
    0.46
     prohib
    0.45
     extractor
    0.44
     extraction
    0.43
     Beverly
    0.43
     interdit
    0.43
     запре
    0.43
    덧
    0.42
     separators
    0.42
     recherches
    0.42
    Activations Density 0.010%

    No Known Activations