© 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. 45537
    Prev
    Next
    INDEX
    Explanations

    to, then, a, too, significantly

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

    protein, jobs, cyclic structure

    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
     मालिकों
    0.50
     JOY
    0.48
     kunj
    0.44
     rikt
    0.43
    喜
    0.42
     Prüfung
    0.41
     toluene
    0.41
     torneo
    0.41
     Bautista
    0.41
     குழந்தைகளுக்கு
    0.41
    POSITIVE LOGITS
    rya
    0.48
    én
    0.46
    ão
    0.43
    ess
    0.42
    angen
    0.40
    emeni
    0.40
    dauer
    0.40
    esehen
    0.39
    }&
    0.39
    assel
    0.39
    Activations Density 0.000%

    No Known Activations