© 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. 163927
    Prev
    Next
    INDEX
    Explanations

    highlighted by, factory, pictures, coupled to

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

    questions and claims

    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
    رفة
    0.49
    كين
    0.49
    لوب
    0.49
    非洲
    0.48
    지만
    0.46
    客厅
    0.46
    룸
    0.46
    荞
    0.46
    рист
    0.45
    кг
    0.45
    POSITIVE LOGITS
     Equations
    0.61
     conductors
    0.55
     upgrades
    0.53
     Switches
    0.53
     @
    0.51
     conductor
    0.51
     upgrading
    0.51
     equations
    0.50
     Is
    0.49
     Reveals
    0.49
    Activations Density 0.000%

    No Known Activations