© 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. 146019
    Prev
    Next
    INDEX
    Explanations

    end of phrase

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

    affirmative responses

    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
    kor
    0.46
     korun
    0.44
     hired
    0.43
    resti
    0.43
    satisfied
    0.42
    н
    0.42
    or
    0.42
    lceil
    0.42
    Kor
    0.42
     tronc
    0.42
    POSITIVE LOGITS
    ደር
    0.52
     अहम
    0.50
     오늘
    0.47
     reserva
    0.46
     reservas
    0.46
     응
    0.46
     KMeans
    0.45
    专
    0.44
     Reserva
    0.44
    यर्स
    0.44
    Activations Density 0.002%

    No Known Activations