© 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. 91677
    Prev
    Next
    INDEX
    Explanations

    unfamiliar

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

    conquered North, understand, modify your

    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
     recharge
    0.52
     undist
    0.48
    ্ধ
    0.48
     پژ
    0.48
     Iglesias
    0.46
     사
    0.45
    nections
    0.45
     maz
    0.45
     モ
    0.44
    Lm
    0.44
    POSITIVE LOGITS
    PRESSED
    0.44
    рін
    0.44
    وقف
    0.44
    我要
    0.42
    웁
    0.41
    असल
    0.41
    环境保护
    0.41
    Epoch
    0.41
     STYLE
    0.40
     Europeo
    0.40
    Activations Density 0.000%

    No Known Activations