© 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. 24615
    Prev
    Next
    INDEX
    Explanations

    competitively priced, in a hurry, distance clinical

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

    distinct, dynamic, steps, went, void

    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
    don
    0.50
    C
    0.47
    stead
    0.47
    feast
    0.46
    โอ
    0.46
    hard
    0.45
     don
    0.44
    T
    0.44
    _
    0.43
    decorator
    0.43
    POSITIVE LOGITS
     আমাকে
    0.46
    િવસ
    0.46
    গারে
    0.44
     zatim
    0.43
     elaboración
    0.42
     substituents
    0.41
    онів
    0.41
    agiarism
    0.41
     pacientes
    0.41
     lawmakers
    0.41
    Activations Density 0.000%

    No Known Activations