© 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. 220532
    Prev
    Next
    INDEX
    Explanations

    fullest extent, Sussex coast, life energy

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

    restrict motion, localized, well stocked

    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
     FabD
    0.51
    ни
    0.48
     bist
    0.43
    みると
    0.42
    ๎
    0.41
    রাগ
    0.41
    。)
    0.41
     demek
    0.41
    Ｓ
    0.40
     …….
    0.40
    POSITIVE LOGITS
     DSA
    0.49
     valide
    0.49
     fech
    0.48
    釉
    0.45
     dizendo
    0.45
     AFI
    0.44
    وزی
    0.44
    안녕하십니까
    0.44
     latitudes
    0.43
     envoy
    0.43
    Activations Density 0.000%

    No Known Activations