© 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. 120472
    Prev
    Next
    INDEX
    Explanations

    how to subscribe or where to find

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

    LLaMA, raw, series, mining, energy

    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
    नायक
    0.52
    दशी
    0.46
     köy
    0.46
     GENERAL
    0.45
    volunteer
    0.44
     猫
    0.44
    getLocation
    0.43
     甲
    0.43
     viajar
    0.42
     Llan
    0.42
    POSITIVE LOGITS
     Bibliothèque
    0.56
     Transl
    0.47
     Proble
    0.46
     macromolecules
    0.46
     Stimulation
    0.46
     hydrochloride
    0.46
     Materialien
    0.46
     sustit
    0.45
     Bibliothek
    0.45
     Gifford
    0.45
    Activations Density 0.001%

    No Known Activations