© 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. 80638
    Prev
    Next
    INDEX
    Explanations

    Lord, animal, massage, regular

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

    specific terms and their contexts

    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
    രാണ്
    0.47
     нач
    0.47
    ்களின்
    0.46
    
    0.46
    Crit
    0.46
    ຯ
    0.46
    }[!
    0.45
    ্স
    0.45
    েশন
    0.45
     начали
    0.45
    POSITIVE LOGITS
     precisely
    0.45
     upon
    0.44
     displaying
    0.44
     sparsely
    0.44
     clouded
    0.42
     strikingly
    0.42
     conspicuously
    0.42
     perverse
    0.42
     mesmo
    0.41
     distant
    0.41
    Activations Density 0.002%

    No Known Activations