© 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. 209737
    Prev
    Next
    INDEX
    Explanations

    introducing descriptions or details

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

    round trip

    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
    밂
    0.52
     σήμερα
    0.51
    궪
    0.49
    πέ
    0.47
    ettamente
    0.47
    hauer
    0.46
    habilitation
    0.45
    лянчук
    0.44
    вери
    0.44
    𝔯
    0.44
    POSITIVE LOGITS
     overturned
    0.50
     sired
    0.49
     happened
    0.47
     fraudulent
    0.47
     crocodiles
    0.46
     crucified
    0.46
     deducted
    0.46
     progressed
    0.44
     floodplain
    0.44
    t
    0.44
    Activations Density 0.001%

    No Known Activations