© 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. 61668
    Prev
    Next
    INDEX
    Explanations

    asking what things mean

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

    explaining 'what does this mean'

    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
    ()>
    0.41
     (>
    0.41
    Volume
    0.40
    म्भ
    0.39
    više
    0.39
     thrice
    0.39
     आरमारा
    0.38
    ཁ
    0.38
    Thirty
    0.38
     сад
    0.38
    POSITIVE LOGITS
     ਅਤੇ
    0.47
     Player
    0.46
     শান্তিপূর্ণ
    0.44
     facilidad
    0.44
     മത്സര
    0.44
     και
    0.44
     বিল্ডিং
    0.43
     για
    0.43
     رپور
    0.42
    besondere
    0.42
    Activations Density 0.000%

    No Known Activations