© 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. 55525
    Prev
    Next
    INDEX
    Explanations

    free demonstrations or special events

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

    academic disciplines and suffixes

    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
    1
    0.55
    ار
    0.48
    ب
    0.48
    ام
    0.46
     Series
    0.46
     Pf
    0.46
    9
    0.46
    7
    0.45
    ي
    0.44
     bf
    0.44
    POSITIVE LOGITS
    EL
    0.57
    ELI
    0.52
     titoli
    0.49
    ຸນ
    0.48
    MORDOR
    0.47
    undu
    0.46
    ául
    0.44
    erven
    0.44
    榆
    0.44
     demurrer
    0.44
    Activations Density 0.000%

    No Known Activations