© 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. 126290
    Prev
    Next
    INDEX
    Explanations

    required, runtime, represents

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

    descriptive adjectives followed by nouns

    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
    聃
    0.51
    惴
    0.47
    ศาส
    0.46
     dlatego
    0.46
    ktCap
    0.46
     médiocrement
    0.45
    Transc
    0.45
    োপাধ
    0.45
    زندگی
    0.44
     poziomie
    0.44
    POSITIVE LOGITS
    ↵
    0.59
     for
    0.55
     it
    0.50
    enc
    0.50
    red
    0.50
     steel
    0.50
    ă
    0.50
      
    0.50
     \"
    0.48
     "
    0.48
    Activations Density 0.002%

    No Known Activations