© 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. 117064
    Prev
    Next
    INDEX
    Explanations

    rented properties

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

    data structures and programming libraries

    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
    υκ
    0.44
    ガネ
    0.43
    selValue
    0.42
    imetry
    0.41
    uvwxyz
    0.41
    אי
    0.40
     sağlan
    0.40
    诉
    0.40
    sız
    0.40
    oids
    0.39
    POSITIVE LOGITS
     cooperatives
    0.45
     greasy
    0.43
     rented
    0.42
     municipios
    0.42
     communes
    0.42
     municípios
    0.41
     grease
    0.40
     escuelas
    0.40
     mounds
    0.40
     principales
    0.39
    Activations Density 0.000%

    No Known Activations