© 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. 228434
    Prev
    Next
    INDEX
    Explanations

    out of something

    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
    ल
    0.86
     surfaces
    0.65
    ка
    0.64
     keluar
    0.64
    र
    0.64
    the
    0.63
    }$.
    0.62
    outside
    0.62
    म
    0.62
     !,
    0.61
    POSITIVE LOGITS
    ä
    0.61
    0.59
    ére
    0.58
     които
    0.57
    ání
    0.56
     два
    0.55
    起了
    0.55
     ktoré
    0.53
    了一些
    0.53
     Ephesus
    0.53
    Activations Density 0.032%

    No Known Activations