© 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. 146078
    Prev
    Next
    INDEX
    Explanations

    premium streamers

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

    gender, neuter, or economic

    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
     ترتيب
    0.48
     مقامات
    0.45
    lü
    0.44
     স্থানীয়
    0.44
     ঘ
    0.44
    شك
    0.43
     நடை
    0.42
    Identifying
    0.41
     ގ
    0.40
    Breaking
    0.40
    POSITIVE LOGITS
     glamorous
    0.59
     wondering
    0.53
     creamy
    0.52
     neuroscience
    0.50
     browser
    0.49
     teaser
    0.49
     prestigious
    0.48
     star
    0.48
     premium
    0.47
     evo
    0.47
    Activations Density 0.000%

    No Known Activations