© 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. 68580
    Prev
    Next
    INDEX
    Explanations

    whatever between fuse photograph hour doubled

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

    excitement, cross, Request, probability, violence, years, glow

    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
     TeV
    0.43
    ហ
    0.43
    上
    0.41
    ត្រូវបាន
    0.41
     transmitters
    0.41
     secreted
    0.40
    起的
    0.40
    記得
    0.39
     recited
    0.39
     stamped
    0.39
    POSITIVE LOGITS
    ഭ്യാ
    0.59
    ździe
    0.52
    𝔂
    0.51
    hydrocèle
    0.50
     "????.??.??"]
    0.50
    nashvillehousing
    0.49
     mayam
    0.48
    odimensional
    0.48
    னே
    0.47
    ofluorescence
    0.47
    Activations Density 0.002%

    No Known Activations