© 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. 190953
    Prev
    Next
    INDEX
    Explanations

    languages and topics

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

    fluid release, flares, ahead

    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
     cair
    0.50
    え
    0.48
     forested
    0.46
     tanah
    0.44
     grazing
    0.44
    万
    0.43
    oo
    0.43
     či
    0.42
     wasnt
    0.42
     smoothly
    0.42
    POSITIVE LOGITS
     उच्चारण
    0.48
     പ്രശ്
    0.47
     ἔ
    0.47
    chev
    0.46
     ईयर
    0.45
     इक्वल
    0.45
     متفاوت
    0.44
     निम्न
    0.44
     എന്നിവ
    0.44
     پڑھ
    0.44
    Activations Density 0.001%

    No Known Activations