© 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. 195014
    Prev
    Next
    INDEX
    Explanations

    expense, Colombia, Equation, propensity, manage, newsletter

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

    bleakness, loss, spectator aspects

    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
    atia
    0.55
    alte
    0.54
    انگ
    0.54
    aise
    0.53
    emor
    0.53
    empire
    0.52
    ა
    0.52
    arist
    0.51
    du
    0.50
    word
    0.50
    POSITIVE LOGITS
     AVAILABLE
    0.50
    Þ
    0.46
     gleiche
    0.45
     grond
    0.45
     opdracht
    0.44
     locomotor
    0.44
    ន្ថ
    0.44
     podm
    0.43
     erő
    0.43
     IMPORTANT
    0.43
    Activations Density 0.000%

    No Known Activations