© 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. 133217
    Prev
    Next
    INDEX
    Explanations

    animal knew

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

    questions and explanations

    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
    ह
    0.56
    her
    0.52
    ya
    0.52
    contrad
    0.52
    ف
    0.52
    an
    0.51
    ش
    0.50
    ha
    0.50
     contradictions
    0.49
    ang
    0.49
    POSITIVE LOGITS
     coefficient
    0.46
     psy
    0.46
     reimburse
    0.46
     സമയ
    0.44
     surprisingly
    0.42
     പെ
    0.42
     McCoy
    0.42
     Coefficient
    0.41
     permanently
    0.41
     watercolor
    0.40
    Activations Density 0.000%

    No Known Activations