© 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. 117452
    Prev
    Next
    INDEX
    Explanations

    four times

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

    articles specifically, fairly extensive

    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
     PLANNING
    0.45
    鄰
    0.45
     പക
    0.44
    мі
    0.43
     తరువాత
    0.43
     যথা
    0.43
    úp
    0.43
     záv
    0.42
    윰
    0.42
     resultArray
    0.42
    POSITIVE LOGITS
    lder
    0.54
     PAOK
    0.49
     overshadow
    0.49
    gcash
    0.48
    Dl
    0.47
    SSI
    0.47
    Kod
    0.46
    SBI
    0.46
    شش
    0.46
     Etr
    0.45
    Activations Density 0.001%

    No Known Activations