© 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. 225595
    Prev
    Next
    INDEX
    Explanations

    full week

    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
     aumentando
    0.58
     aumentare
    0.55
     rotacao
    0.51
    ”，
    0.49
     egip
    0.48
     coorden
    0.47
    Ⲁ
    0.47
     propias
    0.47
     sceGu
    0.47
    াহিনী
    0.46
    POSITIVE LOGITS
    ീ
    0.45
     oph
    0.44
     Petroleum
    0.44
     Phenomenology
    0.44
     Science
    0.43
     Transport
    0.43
    sad
    0.42
     Mortgage
    0.42
     Chemicals
    0.42
     Molecular
    0.41
    Activations Density 0.000%

    No Known Activations