© 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. 46414
    Prev
    Next
    INDEX
    Explanations

    data structures requiring writing

    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
     ஏனெ
    0.58
    omen
    0.52
     Perché
    0.44
    aguan
    0.44
    gua
    0.43
     çünkü
    0.41
    ENS
    0.40
    к
    0.40
    ard
    0.40
    ek
    0.40
    POSITIVE LOGITS
    0.43
     Aurora
    0.43
        
    0.42
     ambigu
    0.42
     phishing
    0.42
     SISO
    0.42
     AutoML
    0.42
     scap
    0.41
     modeled
    0.40
     geheel
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.