© 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. 148909
    Prev
    Next
    INDEX
    Explanations

    giving extended

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

    out of scope exclusions

    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
     Plummer
    0.41
    ’!
    0.41
    
    0.41
     शकेल
    0.40
    )!
    0.39
     Crocker
    0.39
    🥛
    0.39
     Loose
    0.39
     सके
    0.38
    POSITIVE LOGITS
     technical
    0.49
    ቲክ
    0.48
     statistik
    0.47
     computations
    0.45
     टेक्निकल
    0.45
    technical
    0.45
     technische
    0.45
    技术
    0.43
    jenis
    0.42
     техні
    0.42
    Activations Density 0.000%

    No Known Activations