© 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. 137559
    Prev
    Next
    INDEX
    Explanations

    carbon emissions, being eliminated

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

    flowery prose

    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
     VIT
    0.63
     Ă
    0.52
     ENTRE
    0.52
     TEN
    0.52
     assay
    0.50
     también
    0.49
     também
    0.49
     ayrıca
    0.49
     MTN
    0.49
     esperaba
    0.49
    POSITIVE LOGITS
    蚣
    0.46
    держа
    0.45
    inject
    0.44
    CreationFailed
    0.44
     ወይም
    0.44
    Verlag
    0.43
    injection
    0.43
    Veronica
    0.43
    ig
    0.43
    atism
    0.43
    Activations Density 0.001%

    No Known Activations