© 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. 58884
    Prev
    Next
    INDEX
    Explanations

    breaks out

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

    never formally, you might, different apple

    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
     Sheets
    0.43
     Sheet
    0.41
     ñ
    0.41
    谴
    0.41
    礡
    0.41
     Monique
    0.40
     thổi
    0.39
    欣赏
    0.38
    回应
    0.38
     Дмитрий
    0.38
    POSITIVE LOGITS
    z
    0.50
    मस
    0.50
    lly
    0.49
    SAA
    0.49
    oil
    0.48
    y
    0.47
    utiliser
    0.47
    yre
    0.47
    aient
    0.46
    riss
    0.46
    Activations Density 0.000%

    No Known Activations