© 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. 152410
    Prev
    Next
    INDEX
    Explanations

    standards such as

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

    abstract components and programming constructs

    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
    يس
    0.60
    ಯ
    0.59
    inel
    0.55
    妘
    0.52
    ネ
    0.51
    炜
    0.51
    ným
    0.50
    네
    0.50
    開幕
    0.49
    އ
    0.49
    POSITIVE LOGITS
     procedure
    0.46
     Charge
    0.45
     repeat
    0.44
     pip
    0.43
     pipette
    0.43
     Borneo
    0.43
     propellant
    0.42
    েও
    0.42
     shaker
    0.42
     P
    0.41
    Activations Density 0.001%

    No Known Activations