© 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. 83380
    Prev
    Next
    INDEX
    Explanations

    new venture

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

    instructions/conditions

    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
     selectively
    0.45
    隻
    0.45
    ır
    0.43
    ]:
    0.43
    𝒸
    0.42
     इज
    0.42
    级
    0.42
     गिरफ्तार
    0.41
     इन्वेस्टमेंट
    0.41
     pretends
    0.41
    POSITIVE LOGITS
     Ciências
    0.52
    Text
    0.47
    تنا
    0.47
    shape
    0.46
    Auto
    0.46
    t
    0.45
    Hemat
    0.45
    fasta
    0.43
    String
    0.43
    ونه
    0.43
    Activations Density 0.000%

    No Known Activations