© 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. 142365
    Prev
    Next
    INDEX
    Explanations

    security, WIFI, fire, IB

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

    Observability, Reliability, Focus, attributes

    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
     two
    0.63
    1
    0.56
     house
    0.55
    two
    0.54
     de
    0.52
     vic
    0.50
     x
    0.50
    de
    0.49
     way
    0.49
     Northern
    0.48
    POSITIVE LOGITS
    धीश
    0.49
    مثل
    0.49
     отре
    0.48
    omyc
    0.47
     отличи
    0.46
    <unused78>
    0.45
    होस्
    0.45
    BleStatus
    0.45
     EtOAc
    0.45
    вости
    0.44
    Activations Density 0.000%

    No Known Activations