© 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. 48730
    Prev
    Next
    INDEX
    Explanations

    full scope or duration

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

    comparing options

    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
     température
    0.54
     العلماء
    0.50
    temperatur
    0.48
     Đá
    0.47
     કહ્યું
    0.47
     Insulation
    0.46
     மேற்பர
    0.46
    嗽
    0.46
     θερ
    0.46
     ഊ
    0.46
    POSITIVE LOGITS
    codec
    0.46
     anteced
    0.45
    gs
    0.44
     institutional
    0.43
     functor
    0.43
     cls
    0.42
     juggling
    0.42
     mercenary
    0.42
     postseason
    0.42
     oblige
    0.42
    Activations Density 0.000%

    No Known Activations