© 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. 173218
    Prev
    Next
    INDEX
    Explanations

    VPN services

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

    foundation followed by a colon

    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
    殘
    0.50
    がい
    0.50
    س
    0.50
    騏
    0.50
    していた
    0.49
    ْب
    0.48
     ਹੈ
    0.47
     하였다
    0.46
    បញ្ចប់
    0.46
    された
    0.45
    POSITIVE LOGITS
     aka
    0.50
     landscaped
    0.44
     AKA
    0.44
    i
    0.44
     admittedly
    0.44
     conventionally
    0.44
     championed
    0.44
    çon
    0.43
    ir
    0.43
     s
    0.43
    Activations Density 0.001%

    No Known Activations