© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77155
    Prev
    Next
    INDEX
    Explanations

    original measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DEPENDENCIA
    0.47
     Continuando
    0.47
     Catherine
    0.46
     Cristina
    0.46
    ר
    0.46
    ﺘ
    0.46
    <0xA1>
    0.45
     linda
    0.45
    黒
    0.45
     lmao
    0.45
    POSITIVE LOGITS
    Selection
    0.43
    ance
    0.42
    akar
    0.42
    ,
    0.42
    ods
    0.41
    k
    0.40
    ardin
    0.40
    ख़
    0.40
    aste
    0.39
    se
    0.39
    Activations Density 0.001%

    No Known Activations