© 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. 143555
    Prev
    Next
    INDEX
    Explanations

    Matthew citations and heaven

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

    Matthew usage

    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
     uncond
    0.45
    رداری
    0.43
    стики
    0.43
    ozems
    0.40
    🚃
    0.38
    രുവ
    0.38
    ccionar
    0.38
     terroir
    0.38
    ｍｍ
    0.38
     molle
    0.38
    POSITIVE LOGITS
    Ἠ
    0.44
     Goto
    0.43
    情绪
    0.42
     PIR
    0.41
    plate
    0.41
     yak
    0.41
    Goto
    0.41
    Hurricane
    0.41
     plate
    0.40
    INF
    0.40
    Activations Density 0.037%

    No Known Activations