© 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. 169261
    Prev
    Next
    INDEX
    Explanations

    heater combined

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

    Summer weather and seasons

    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
     संके
    0.48
     âmbito
    0.46
    льні
    0.46
    ńst
    0.44
     eixo
    0.44
    棚
    0.44
    льному
    0.43
    क्सी
    0.43
     estre
    0.43
    othesis
    0.43
    POSITIVE LOGITS
     *}\
    0.46
     PAOK
    0.45
    標
    0.44
     ϒ
    0.43
    StudentNo
    0.42
     SPIR
    0.42
    Instances
    0.42
     hodnot
    0.41
    峮
    0.41
     TRUST
    0.41
    Activations Density 0.000%

    No Known Activations