© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79200
    Prev
    Next
    INDEX
    Explanations

    datasets whenever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    0.51
     coatings
    0.47
    PG
    0.47
    PY
    0.44
    pian
    0.43
    PP
    0.41
     rotated
    0.41
    Parent
    0.40
    Use
    0.40
    EQ
    0.39
    POSITIVE LOGITS
     dimanche
    0.54
     言
    0.50
     escritor
    0.47
     plufieurs
    0.47
     பல்வேறு
    0.47
     parlato
    0.46
     samedi
    0.46
     Estudos
    0.46
     сервера
    0.46
     diverses
    0.45
    Activations Density 0.001%

    No Known Activations