© 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. 62366
    Prev
    Next
    INDEX
    Explanations

    potential needs

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

    professional or technical terms

    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
     ഇത്
    0.63
     ไม่
    0.62
    ?!
    0.62
     รถ
    0.59
     тяжело
    0.59
     It
    0.58
     Stretching
    0.58
     I
    0.58
    一样的
    0.58
     അത്
    0.57
    POSITIVE LOGITS
     streamlined
    0.55
     calendars
    0.53
     alphan
    0.53
     alphanumeric
    0.53
    스의
    0.52
     fingertips
    0.51
    的三
    0.51
     cybersecurity
    0.50
     hurdle
    0.50
     tetrachloride
    0.50
    Activations Density 0.000%

    No Known Activations