© 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. 222659
    Prev
    Next
    INDEX
    Explanations

    share of / gas line / cosmetics packaging

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

    stone hides, steeds to, Data Science, online predators

    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
    0.53
    FORMAT
    0.51
    PRODUCTION
    0.51
     Optionally
    0.50
    STRA
    0.49
     FORMAT
    0.49
     baku
    0.49
    l
    0.47
    UN
    0.47
    PARAM
    0.45
    POSITIVE LOGITS
    áni
    0.50
    áln
    0.43
    ofe
    0.43
     más
    0.43
    atele
    0.42
    cia
    0.42
     cały
    0.42
    ảng
    0.42
     центр
    0.41
    ían
    0.41
    Activations Density 0.001%

    No Known Activations