© 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. 96927
    Prev
    Next
    INDEX
    Explanations

    voltage presentation friends physical gifts opinions

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

    atmosphere is

    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
    หรับ
    0.49
    নান
    0.48
    মতি
    0.46
    лица
    0.46
    㓞
    0.45
     DEPENDENCIA
    0.45
     conced
    0.45
    <unused38>
    0.44
     granted
    0.44
    যদিও
    0.44
    POSITIVE LOGITS
    ä
    0.46
    chemistry
    0.46
    Vt
    0.44
     مس
    0.43
     cathode
    0.43
    ッジ
    0.43
    Chemistry
    0.43
     chemistry
    0.42
     youtube
    0.42
    à
    0.42
    Activations Density 0.000%

    No Known Activations