© 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. 21443
    Prev
    Next
    INDEX
    Explanations

    the Supreme, the first

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

    privacy username settings

    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
     kalan
    0.46
     F
    0.43
     random
    0.43
     Day
    0.43
     kal
    0.43
     journalists
    0.42
    Day
    0.41
    unden
    0.41
     R
    0.41
    ev
    0.41
    POSITIVE LOGITS
    𝔦
    0.55
    竰
    0.54
     degrés
    0.54
    𝘆
    0.52
    𝔞
    0.51
     તરીકે
    0.51
    사업
    0.50
    媤
    0.50
    輌
    0.49
     યોજના
    0.49
    Activations Density 0.000%

    No Known Activations