© 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. 209520
    Prev
    Next
    INDEX
    Explanations

    need to

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

    air to circulate all around

    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
    _
    0.47
     जिनकी
    0.46
     IMPORTANT
    0.44
    ھ
    0.44
    awatts
    0.44
     PDF
    0.43
    awatt
    0.42
    計
    0.42
    (_
    0.41
     NV
    0.41
    POSITIVE LOGITS
     வீடு
    0.53
    apar
    0.46
    高志森
    0.44
     aktor
    0.44
     perv
    0.44
    liter
    0.44
    னைய
    0.44
    )^{*}
    0.44
    Overlay
    0.43
     filtra
    0.43
    Activations Density 0.000%

    No Known Activations