© 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. 122736
    Prev
    Next
    INDEX
    Explanations

    support programme entrant

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

    Handle special cases

    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
     pathway
    0.46
     gallbladder
    0.45
     bassa
    0.44
     nao
    0.44
    }
    0.44
     algorithms
    0.44
     low
    0.44
     titration
    0.43
     register
    0.43
     wob
    0.43
    POSITIVE LOGITS
    inverted
    0.47
    ivel
    0.46
    effet
    0.46
     لیے
    0.46
    vl
    0.45
    allaitement
    0.44
    などが
    0.44
    Ე
    0.43
    िनेट
    0.42
     descubre
    0.42
    Activations Density 0.000%

    No Known Activations