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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34803
    Prev
    Next
    INDEX
    Explanations

    testing messages, hair, following, inadvertently, data, entering, taller, Ionic, Load

    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
    annual
    0.36
     bốn
    0.36
     नाउ
    0.36
    shal
    0.35
    䒷
    0.34
     BLO
    0.34
    祈
    0.33
    貥
    0.33
    rito
    0.33
     Som
    0.33
    POSITIVE LOGITS
     अफवाह
    0.41
     rape
    0.38
     rumors
    0.38
    قة
    0.37
    Horizon
    0.37
     accurate
    0.37
    Xa
    0.37
     contral
    0.36
     custodia
    0.36
    šč
    0.36
    Activations Density 0.000%

    No Known Activations