© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21247
    Prev
    Next
    INDEX
    Explanations

    Abdul Kalam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     стоковая
    -1.57
     新年
    -1.49
     правительства
    -1.45
    ♡♡
    -1.44
    💪
    -1.43
    ♥️
    -1.43
     многих
    -1.43
    تفسير
    -1.42
    مقال
    -1.41
     великолеп
    -1.41
    POSITIVE LOGITS
     their
    2.47
     are
    1.68
     every
    1.45
     any
    1.41
     each
    1.39
     weren
    1.38
     और
    1.37
     they
    1.37
     didn
    1.37
     another
    1.35
    Activations Density 0.006%

    No Known Activations