© 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. 33509
    Prev
    Next
    INDEX
    Explanations

    personal and business assets

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

    how data is processed

    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
     riddle
    0.46
    ቭ
    0.46
     fetish
    0.45
     vaginalis
    0.45
     concealer
    0.44
     takeoff
    0.43
     MISSION
    0.43
     nonprofit
    0.43
     hairstyle
    0.42
     논
    0.41
    POSITIVE LOGITS
     الخامس
    0.46
    rosion
    0.46
     ಶತ
    0.44
    ig
    0.44
    меня
    0.44
     लिं
    0.44
    astern
    0.43
    headings
    0.43
    ink
    0.42
    marc
    0.42
    Activations Density 0.000%

    No Known Activations