© 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. 222603
    Prev
    Next
    INDEX
    Explanations

    vegans, ago, style, illness

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

    but contrasting information

    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
    ચારી
    0.55
     Qualquer
    0.53
    cliente
    0.52
     cliquer
    0.52
    plotting
    0.52
    蓦
    0.52
    prits
    0.50
     सामग्रियों
    0.50
    texte
    0.50
    ಿರಿ
    0.49
    POSITIVE LOGITS
    ↵
    0.56
    :
    0.55
    (
    0.51
    4
    0.50
     proxies
    0.49
    Transition
    0.48
    0.48
    2
    0.47
     none
    0.47
     क्या
    0.46
    Activations Density 0.001%

    No Known Activations