© 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. 33215
    Prev
    Next
    INDEX
    Explanations

    international or non-English characters

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

    tasks, rave, loss

    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
    ul
    0.52
    abri
    0.47
    ulit
    0.45
     मैदान
    0.44
    r
    0.44
     |\
    0.43
    and
    0.43
    ouri
    0.43
    abord
    0.43
    rider
    0.42
    POSITIVE LOGITS
    ﻰ
    0.48
    ക്കാല
    0.48
    ﺲ
    0.46
    쟁
    0.45
    শৃঙ্খলা
    0.42
    WHAT
    0.41
    엇
    0.41
    湛
    0.40
    IGHT
    0.40
    SetValue
    0.40
    Activations Density 0.001%

    No Known Activations