© 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. 88957
    Prev
    Next
    INDEX
    Explanations

    non-english characters

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

    adhere to terms and conditions

    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
     indices
    0.45
     gezien
    0.44
     booted
    0.44
     contests
    0.43
    <strong>
    0.42
     ospiti
    0.41
     equipes
    0.41
     sanitized
    0.41
     administrations
    0.40
     inspector
    0.40
    POSITIVE LOGITS
    ຈ
    0.57
     கல்விய
    0.55
    เอียด
    0.49
     امیدوار
    0.49
     அடிப்படை
    0.49
    ផ្ត
    0.48
    viation
    0.48
    holiday
    0.47
     ადამიან
    0.47
     கடல்
    0.47
    Activations Density 0.000%

    No Known Activations