© 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. 183914
    Prev
    Next
    INDEX
    Explanations

    who would

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

    addressing problems and solutions

    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
     game
    0.45
    ania
    0.44
     Rather
    0.44
     i
    0.42
     B
    0.42
    onial
    0.41
    onian
    0.41
     Rip
    0.41
    لوں
    0.41
    の種類
    0.41
    POSITIVE LOGITS
    ЕН
    0.54
    द
    0.52
    𝘥
    0.52
     neumáticos
    0.51
    דר
    0.48
    츈
    0.48
    दु
    0.46
    ⵃ
    0.46
     trasero
    0.46
    ዃ
    0.46
    Activations Density 0.001%

    No Known Activations