© 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. 36834
    Prev
    Next
    INDEX
    Explanations

    specific listings or information

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

    specific philosophy

    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
     kerap
    0.51
    ब
    0.49
     easing
    0.46
    ;\
    0.45
    ona
    0.44
    ēs
    0.44
    n
    0.44
    берём
    0.43
    <0xA8>
    0.43
     deterior
    0.43
    POSITIVE LOGITS
     Ato
    0.48
    Prefs
    0.46
     లేదు
    0.45
     Orche
    0.44
     Inhalte
    0.44
    Listo
    0.44
    Are
    0.44
    Oi
    0.43
     내용을
    0.43
    uşt
    0.43
    Activations Density 0.000%

    No Known Activations