© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 161651
    Prev
    Next
    INDEX
    Explanations

    ambitious art and chamber music

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

    sections of things

    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
    ო
    0.48
    }^{*}
    0.47
    얗
    0.46
    吒
    0.45
    away
    0.43
    fum
    0.42
    滕
    0.41
    gF
    0.41
    降
    0.41
    fbox
    0.41
    POSITIVE LOGITS
     ज्ये
    0.53
     بق
    0.52
    amsu
    0.52
    hetam
    0.52
     Jok
    0.51
     with
    0.50
     अं
    0.50
     сопрово
    0.50
     பகுதியில்
    0.49
     भागा
    0.49
    Activations Density 0.000%

    No Known Activations