© 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. 99530
    Prev
    Next
    INDEX
    Explanations

    banning and access restrictions

    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
    充足
    0.39
     Ruff
    0.38
     NotImplemented
    0.38
    Լ
    0.38
    ینه
    0.37
    ரூ
    0.37
    Newly
    0.37
     polarised
    0.36
     appliqué
    0.36
     phù
    0.35
    POSITIVE LOGITS
     counts
    0.37
     त्याचा
    0.36
     dzien
    0.35
    ⸩
    0.35
    淹
    0.35
    ewomen
    0.35
     Segal
    0.34
    producto
    0.34
    स्तान
    0.34
     Hartree
    0.34
    Activations Density 0.000%

    No Known Activations