© 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. 109726
    Prev
    Next
    INDEX
    Explanations

    except through

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

    argue, believe, refine

    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
     jogos
    0.50
    䔋
    0.50
    㸵
    0.50
     Giải
    0.49
    <unused22>
    0.48
     قانون
    0.47
     quả
    0.46
     النج
    0.46
     zwycię
    0.46
     Awak
    0.46
    POSITIVE LOGITS
    rado
    0.45
    lf
    0.43
    <0x0D>
    0.42
    era
    0.42
    ステ
    0.42
    ㅈ
    0.42
    long
    0.41
    8
    0.41
    olyb
    0.41
    lide
    0.41
    Activations Density 0.002%

    No Known Activations