© 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. 98699
    Prev
    Next
    INDEX
    Explanations

    will come or and he.she

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

    recommend

    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
    .
    0.49
     novices
    0.43
    Dancing
    0.43
     adaptée
    0.42
     Muchas
    0.41
    မယ်
    0.41
     bling
    0.41
     Genres
    0.41
     mosa
    0.40
     包括
    0.40
    POSITIVE LOGITS
    ert
    0.47
     DoD
    0.47
     egregious
    0.46
    衄
    0.44
    പ്പെട്ട
    0.43
    ült
    0.43
    えた
    0.43
    かれた
    0.43
    ilt
    0.42
    during
    0.42
    Activations Density 0.001%

    No Known Activations