© 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. 14802
    Prev
    Next
    INDEX
    Explanations

    Maria LA

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

    abbreviations or initialisms

    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
    <unused74>
    0.50
     secondNumber
    0.49
     imageHeight
    0.49
     نهاية
    0.49
    缴纳
    0.48
     недвижи
    0.47
    স্থানীয়
    0.47
    वर्धन
    0.47
    <unused75>
    0.46
    getApplication
    0.46
    POSITIVE LOGITS
     B
    0.89
     S
    0.88
     T
    0.87
     P
    0.82
     D
    0.81
    G
    0.81
     C
    0.80
     N
    0.79
    T
    0.79
    P
    0.79
    Activations Density 0.085%

    No Known Activations