© 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. 55133
    Prev
    Next
    INDEX
    Explanations

    requesting more details

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

    form and shape

    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
    Alles
    0.44
    餸
    0.43
    ouest
    0.42
    ుల
    0.41
    زاده
    0.41
    阊
    0.41
    чы
    0.40
    AppBarLayout
    0.40
    <0x80>
    0.39
    subfigure
    0.39
    POSITIVE LOGITS
     difíciles
    0.55
    odis
    0.47
     γιατί
    0.46
     život
    0.46
    SAS
    0.45
     gravit
    0.44
    adies
    0.44
     ثلاث
    0.43
     φι
    0.43
     pernicious
    0.43
    Activations Density 0.000%

    No Known Activations