© 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. 49000
    Prev
    Next
    INDEX
    Explanations

    the contents, the device

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

    divides | of

    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
    Playlist
    0.53
    㧍
    0.51
    Consulta
    0.50
     условия
    0.50
    лист
    0.47
     deuda
    0.47
    άνει
    0.46
     contraseña
    0.45
     Validación
    0.45
    ﻧ
    0.44
    POSITIVE LOGITS
     sympathetic
    0.46
     unsuspecting
    0.46
     (#
    0.45
     equilateral
    0.45
     Abelian
    0.44
     conferencing
    0.44
     whack
    0.43
     grassy
    0.42
     planar
    0.42
     quãng
    0.41
    Activations Density 0.000%

    No Known Activations