© 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. 32647
    Prev
    Next
    INDEX
    Explanations

    evidence for claims

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

    evidence inquiry

    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
    é
    0.76
    ri
    0.64
    spolit
    0.63
    sc
    0.62
    lr
    0.59
     forstå
    0.59
     जोख
    0.58
    ci
    0.57
    dü
    0.56
    ss
    0.55
    POSITIVE LOGITS
     evidence
    0.77
    evidence
    0.75
    Evidence
    0.74
    <0x80>
    0.70
     Evidence
    0.69
    证据
    0.69
    修
    0.68
    證據
    0.65
     evidencia
    0.64
     EVIDENCE
    0.64
    Activations Density 0.017%

    No Known Activations