© 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. 131301
    Prev
    Next
    INDEX
    Explanations

    finding goods industries

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

    not depicting explicit sexual or graphic acts

    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
     AIA
    0.49
     COUNCIL
    0.45
     organizar
    0.44
    >∞</
    0.43
    ਸੀਂ
    0.42
     месе
    0.42
     जियोग्राफी
    0.42
    ２
    0.41
    Provided
    0.41
     мене
    0.41
    POSITIVE LOGITS
    (`${
    0.44
    ("$
    0.43
     `${
    0.42
    ('.'
    0.42
    ('(
    0.41
    cig
    0.41
     nip
    0.41
    jn
    0.40
     $((
    0.40
    ◟
    0.40
    Activations Density 0.000%

    No Known Activations