© 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. 78528
    Prev
    Next
    INDEX
    Explanations

    roads and gas

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

    goals and code patterns

    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
     因为
    0.52
    Prints
    0.47
    ך
    0.47
    лэ
    0.46
    NameValuePair
    0.45
     конструкции
    0.44
    fton
    0.44
    in
    0.44
    が必要
    0.44
    Ђ
    0.43
    POSITIVE LOGITS
     engulfed
    0.52
     levelled
    0.50
     annihilated
    0.50
     attractiveness
    0.48
     star
    0.47
     سر
    0.47
     cheating
    0.46
     मुद्दे
    0.46
     सड़कें
    0.46
     obedience
    0.46
    Activations Density 0.000%

    No Known Activations