© 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. 106132
    Prev
    Next
    INDEX
    Explanations

    know how

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

    extreme cold, prevents wandering

    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
    па
    0.48
    ка
    0.47
    тий
    0.46
    अर्
    0.46
    ಾಪ
    0.45
    Ĭ
    0.45
     divorced
    0.45
    Кли
    0.45
    ガ
    0.45
    evich
    0.43
    POSITIVE LOGITS
    slan
    0.53
    ított
    0.52
     그랬
    0.52
     লই
    0.50
     দম
    0.49
     tivemos
    0.47
    enni
    0.46
     kW
    0.46
     amplit
    0.46
     tuvimos
    0.46
    Activations Density 0.000%

    No Known Activations