© 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. 131920
    Prev
    Next
    INDEX
    Explanations

    What followed by your or skin or side

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

    pale, lighter, or similar

    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
    𝙘
    0.55
    𝙡
    0.53
    yı
    0.53
    𝘸
    0.53
    𝓎
    0.52
    ي
    0.52
     ზ
    0.52
     انقل
    0.51
    𝚍
    0.50
     وګ
    0.50
    POSITIVE LOGITS
     substitutions
    0.49
    validation
    0.46
    APs
    0.46
    ANA
    0.45
     carriages
    0.45
    Native
    0.44
    Information
    0.44
     contingent
    0.44
    ions
    0.43
     payments
    0.43
    Activations Density 0.000%

    No Known Activations