© 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. 31388
    Prev
    Next
    INDEX
    Explanations

    hygge and excellence

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

    gardens making metros

    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
    (!)
    0.53
    大きさ
    0.52
     lots
    0.51
     (!)
    0.47
     Bauch
    0.45
    甲
    0.45
     와
    0.44
     вкус
    0.44
    вано
    0.43
     getters
    0.43
    POSITIVE LOGITS
    supabase
    0.49
    ในช่วง
    0.47
    during
    0.45
    jetty
    0.44
    လေး
    0.43
    询
    0.42
    idescent
    0.41
    romantic
    0.41
    imgPath
    0.41
    fragment
    0.41
    Activations Density 0.000%

    No Known Activations