© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23097
    Prev
    Next
    INDEX
    Explanations

    I, we, He actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نیشنل
    0.43
     є
    0.43
    臧
    0.43
     את
    0.42
    を含む
    0.42
     ہے۔
    0.42
    <unused2125>
    0.42
     ഇ
    0.42
    汢
    0.42
    罒
    0.41
    POSITIVE LOGITS
     didn
    0.79
     hadn
    0.68
     forgot
    0.67
     want
    0.63
     had
    0.60
     lacked
    0.60
     felt
    0.57
     cannot
    0.56
     chose
    0.56
     overcame
    0.56
    Activations Density 0.016%

    No Known Activations