© 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. 174184
    Prev
    Next
    INDEX
    Explanations

    EU battery terminal

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

    two categories

    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
    I
    0.56
    0.52
    S
    0.49
    A
    0.49
     to
    0.46
    Σ
    0.45
    Business
    0.44
    Ø
    0.44
     –
    0.44
    TF
    0.44
    POSITIVE LOGITS
     لال
    0.53
    romino
    0.51
     ਹਨ
    0.50
    ра
    0.50
     копия
    0.49
    ्यूस
    0.48
    ytes
    0.48
     тесто
    0.47
     אס
    0.47
    𝗲
    0.47
    Activations Density 0.000%

    No Known Activations