© 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. 11391
    Prev
    Next
    INDEX
    Explanations

    Several international

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

    measurements and text generation

    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
     menschen
    0.55
     saloon
    0.51
     veterans
    0.50
     toured
    0.50
     perceives
    0.50
     nakon
    0.50
     폭
    0.49
     prédio
    0.49
     prisão
    0.48
     vetor
    0.47
    POSITIVE LOGITS
    من
    0.46
    ئ
    0.46
    nX
    0.44
    mx
    0.42
    ulants
    0.42
     Thickness
    0.41
    upy
    0.41
    剜
    0.40
    薄
    0.40
     Szer
    0.39
    Activations Density 0.000%

    No Known Activations