© 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. 73040
    Prev
    Next
    INDEX
    Explanations

    caravan

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

    gentle pressure

    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
     이게
    0.45
     Atkinson
    0.44
     London
    0.44
     Hudson
    0.41
    estimate
    0.41
     Pompe
    0.40
     Hud
    0.40
    </sup>
    0.39
     Pl
    0.39
     Sunset
    0.39
    POSITIVE LOGITS
     antioxidants
    0.56
     apoptosis
    0.54
    こともある
    0.54
     antioxid
    0.52
    蛋白质
    0.52
     antioxidant
    0.49
    apopt
    0.48
     comorbidities
    0.48
     韓国
    0.47
     viruses
    0.47
    Activations Density 0.001%

    No Known Activations