© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 121163
    Prev
    Next
    INDEX
    Explanations

    locations and drying

    np_acts-logits-general · gemini-2.5-flash-lite

    ranking factors and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.45
     Trademark
    0.43
     Ultraviolet
    0.43
     inductance
    0.42
     Alignment
    0.42
    hong
    0.42
     Efficiency
    0.42
     Attack
    0.41
     Effectiveness
    0.41
    }")
    0.41
    POSITIVE LOGITS
    كال
    0.47
    omen
    0.47
    یس
    0.46
    čar
    0.45
    被告
    0.45
     få
    0.44
     surreal
    0.44
     puk
    0.44
    kör
    0.43
    दिव
    0.43
    Activations Density 0.000%

    No Known Activations