© 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. 188990
    Prev
    Next
    INDEX
    Explanations

    specific conditions or disclosures

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

    Okay

    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
    ত্রে
    0.50
     discrimination
    0.50
    ни
    0.48
    setDescription
    0.47
     প
    0.46
    setTitle
    0.46
    на
    0.44
     vide
    0.43
    cargar
    0.43
     pour
    0.43
    POSITIVE LOGITS
    ็อก
    0.46
    🦢
    0.45
    kans
    0.43
    codiles
    0.42
    かわいい
    0.42
    ಬ್ಬಿಣ
    0.41
    ]}$
    0.40
    Σ
    0.40
    Imidazole
    0.40
    沦
    0.39
    Activations Density 0.002%

    No Known Activations