© 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. 18994
    Prev
    Next
    INDEX
    Explanations

    citations and sourced information

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

    crystal meth

    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
    caused
    0.52
    cultured
    0.50
    could
    0.49
    곡
    0.49
    fraction
    0.49
    becomes
    0.49
    V
    0.49
    collection
    0.49
    path
    0.48
    ca
    0.48
    POSITIVE LOGITS
     Waver
    0.48
    あなた
    0.46
     Breaking
    0.46
     recetas
    0.45
    帮你
    0.44
    柺
    0.44
     penilaian
    0.44
    ுற
    0.43
    ﺵ
    0.43
     breaking
    0.43
    Activations Density 0.000%

    No Known Activations