© 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. 107543
    Prev
    Next
    INDEX
    Explanations

    sequence completion

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

    series countries abide allows Temple mirror

    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
     promoc
    0.50
    ě
    0.46
    纯
    0.46
    "`
    0.45
    )"><
    0.44
     interesa
    0.44
    )`
    0.43
    кина
    0.42
     allí
    0.42
    язви
    0.42
    POSITIVE LOGITS
     조
    0.48
     limo
    0.48
     tuning
    0.47
     اگر
    0.45
    ໂຕ
    0.44
    監査
    0.43
     گر
    0.42
     교통
    0.42
    tiles
    0.42
     soliton
    0.42
    Activations Density 0.002%

    No Known Activations