© 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. 29923
    Prev
    Next
    INDEX
    Explanations

    unlike traditional

    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
     this
    0.79
     he
    0.62
     and
    0.58
    T
    0.54
     as
    0.52
    ствия
    0.51
     we
    0.51
    this
    0.51
     alphabetical
    0.51
     it
    0.50
    POSITIVE LOGITS
    il
    0.62
    ших
    0.61
    ir
    0.61
    uz
    0.60
    end
    0.60
    ig
    0.59
    uk
    0.59
    א
    0.58
    ach
    0.57
    gebaut
    0.57
    Activations Density 0.003%

    No Known Activations