© 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. 127237
    Prev
    Next
    INDEX
    Explanations

    highest ground

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

    size and quantity

    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
     руки
    0.46
     menyebut
    0.46
    rescue
    0.46
     rescat
    0.45
    Rescue
    0.45
    ource
    0.44
     rescues
    0.44
     件
    0.43
    Calling
    0.42
    ｳ
    0.42
    POSITIVE LOGITS
     Synth
    0.47
     Salsa
    0.46
     Semin
    0.45
    ților
    0.43
    ządz
    0.43
     এডিনবার্গ
    0.43
     Samantha
    0.42
     zásob
    0.42
     whist
    0.42
    များနှင့်
    0.42
    Activations Density 0.000%

    No Known Activations