© 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. 152385
    Prev
    Next
    INDEX
    Explanations

    agent presents

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

    help brainstorming ideas

    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
     வைத்து
    0.47
    asmine
    0.47
    prising
    0.47
    চার
    0.44
     Hours
    0.44
    旎
    0.42
    钿
    0.41
    痹
    0.41
     Variance
    0.41
     Curves
    0.40
    POSITIVE LOGITS
     planejamento
    0.55
     corporates
    0.52
     investimentos
    0.52
     retires
    0.50
    Retired
    0.48
     букмекер
    0.48
     exercer
    0.48
     dépens
    0.47
     GUAR
    0.47
     LMFBR
    0.46
    Activations Density 0.000%

    No Known Activations