© 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. 3539
    Prev
    Next
    INDEX
    Explanations

    small contiguous album product world origin

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

    specific ordering or use case

    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
    ↵↵
    0.65
    ↵
    0.59
     i
    0.54
     =
    0.54
    leading
    0.53
    にか
    0.52
    <eos>
    0.51
     e
    0.51
     can
    0.51
    party
    0.50
    POSITIVE LOGITS
    ܘܢ
    0.55
     జరిగిన
    0.54
     ದೊಡ್ಡ
    0.53
    盱
    0.52
    很大的
    0.52
     größte
    0.52
    Ꮙ
    0.52
    铷
    0.52
     ತುಂಬಾ
    0.51
    㓦
    0.51
    Activations Density 0.000%

    No Known Activations