© 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. 45819
    Prev
    Next
    INDEX
    Explanations

    crucial help responsible free beautiful

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

    cultural studies and images

    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
     manifold
    0.51
     usc
    0.50
     AE
    0.50
    ين
    0.49
     manifolds
    0.48
    ﻷ
    0.47
     SPI
    0.46
     ψ
    0.45
     subcut
    0.45
     ORI
    0.43
    POSITIVE LOGITS
    theorem
    0.48
    ционные
    0.47
    igste
    0.46
    uvat
    0.45
    Ml
    0.45
     ज्योग्राफी
    0.45
    <0xBB>
    0.44
    मक
    0.43
     कोट
    0.43
    грамма
    0.43
    Activations Density 0.000%

    No Known Activations