© 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. 21562
    Prev
    Next
    INDEX
    Explanations

    stunning places and architecture

    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
    ER
    0.47
    지만
    0.46
    梦
    0.45
    UNIVERS
    0.43
    UT
    0.43
    PE
    0.42
    UBE
    0.42
    jl
    0.42
    ösungen
    0.41
    W
    0.40
    POSITIVE LOGITS
     deciding
    0.49
     testimonio
    0.48
     decisione
    0.48
     किल्ला
    0.47
     decide
    0.46
     ከአ
    0.46
     partida
    0.46
     decides
    0.46
     decisión
    0.46
    oporosis
    0.45
    Activations Density 0.006%

    No Known Activations