© 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. 37884
    Prev
    Next
    INDEX
    Explanations

    initial prompting

    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
     dígitos
    0.49
     toneladas
    0.47
    ბ
    0.46
    וני
    0.46
     esenciales
    0.44
     потер
    0.43
    imagenes
    0.43
    ཌ
    0.43
     débil
    0.42
     액세
    0.42
    POSITIVE LOGITS
    neath
    0.45
     prompting
    0.45
    dispose
    0.45
    PSO
    0.44
    kyo
    0.43
    Cause
    0.42
    attva
    0.42
     rethinking
    0.42
     dispose
    0.41
    Medicine
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.