© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143151
    Prev
    Next
    INDEX
    Explanations

    not okay

    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
    irrahim
    0.55
    ⟧
    0.51
     costitu
    0.50
     hinzu
    0.50
    വിലെ
    0.50
    ivers
    0.49
     Hfn
    0.49
     العلام
    0.49
     ယ
    0.48
     höhere
    0.48
    POSITIVE LOGITS
    தான
    0.45
    anza
    0.41
    anke
    0.40
    Runtime
    0.40
    они
    0.39
    aul
    0.39
    ант
    0.39
     требо
    0.39
    anan
    0.38
    ాన
    0.37
    Activations Density 0.000%

    No Known Activations