© 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. 42077
    Prev
    Next
    INDEX
    Explanations

    curious, interested, entertainment, advertising, Lord <ctrl63>

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

    technical code and documentation

    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
     ತಿಳ
    0.55
     এমন
    0.47
     ప్రస్తుతం
    0.46
     دائما
    0.46
     heavenly
    0.45
     जाणून
    0.45
     古
    0.44
    が得
    0.44
     که
    0.44
     ধাতু
    0.44
    POSITIVE LOGITS
    спублі
    0.51
    φέ
    0.49
    sp
    0.48
    änder
    0.46
    isierung
    0.46
    ms
    0.46
    the
    0.46
     Appropri
    0.46
     ContentView
    0.45
    منابع
    0.45
    Activations Density 0.000%

    No Known Activations