© 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. 48409
    Prev
    Next
    INDEX
    Explanations

    anything stated

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

    irrational, logical, not logical, illogical

    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
     優
    0.59
     определя
    0.49
     తొలి
    0.49
     పలు
    0.48
    ilte
    0.48
    gesamt
    0.46
     เฮ
    0.46
     герои
    0.45
     ภาพ
    0.45
     よう
    0.44
    POSITIVE LOGITS
     applic
    0.45
     denomin
    0.45
     circon
    0.45
     telemetry
    0.44
    ф
    0.43
    ട്ടം
    0.42
     bary
    0.42
     mathematicians
    0.42
     regards
    0.42
    BYTES
    0.42
    Activations Density 0.000%

    No Known Activations