© 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. 27529
    Prev
    Next
    INDEX
    Explanations

    liposuction

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

    liposuction, startups, flexibility, puckering, rid of, under each, not falling, grounding conductors, hair removal

    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
    aaS
    0.50
    (\
    0.49
    Z
    0.48
     patented
    0.47
     services
    0.45
    Award
    0.45
    (
    0.45
    Block
    0.45
    9
    0.44
    AA
    0.44
    POSITIVE LOGITS
     Ако
    0.49
     دیگه
    0.48
     少し
    0.47
     dalších
    0.46
     Shouldn
    0.46
     ragazzo
    0.44
    abbanti
    0.44
    癬
    0.44
     atleta
    0.44
     lessened
    0.43
    Activations Density 0.005%

    No Known Activations