© 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. 164816
    Prev
    Next
    INDEX
    Explanations

    amazon urls and product identifiers

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

    official names and concepts

    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
    என்ன
    0.48
     controle
    0.48
    шою
    0.48
     حاج
    0.47
    ylsulfanyl
    0.47
    UPA
    0.47
    نىڭ
    0.47
    <unused82>
    0.46
    tDBOutput
    0.46
    کہ
    0.46
    POSITIVE LOGITS
     Gaia
    0.51
    0.50
     booklets
    0.46
     Strip
    0.45
     Enhancement
    0.45
     Blank
    0.44
     Early
    0.43
    奇
    0.42
    เก
    0.42
     Affinity
    0.42
    Activations Density 0.000%

    No Known Activations