© 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. 196388
    Prev
    Next
    INDEX
    Explanations

    be giving / be offering

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

    students protesting, facial nerve, for artists

    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
     หนังสือ
    0.47
     กิน
    0.44
     observability
    0.44
     あなた
    0.44
     osmosis
    0.44
     Baume
    0.44
    𒋛
    0.44
     BUN
    0.43
     prob
    0.43
     FOUR
    0.43
    POSITIVE LOGITS
    keras
    0.50
    pia
    0.47
    n
    0.45
    mias
    0.45
    s
    0.45
    گون
    0.44
    imba
    0.44
    rians
    0.43
    nid
    0.43
    xie
    0.43
    Activations Density 0.001%

    No Known Activations