© 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. 24060
    Prev
    Next
    INDEX
    Explanations

    probability and likelihood

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

    facilitate harm or abuse

    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
    했지만
    0.46
     लेकिन
    0.40
     dimulai
    0.37
     comenzamos
    0.37
    되며
    0.36
    /
    0.36
    力和
    0.35
     nhưng
    0.34
     включая
    0.34
    ,
    0.34
    POSITIVE LOGITS
     probablemente
    0.41
    溶液
    0.40
     நிச்சயமாக
    0.39
     pewno
    0.38
     probably
    0.38
     provavelmente
    0.37
     likely
    0.36
     prawdopod
    0.36
     Probably
    0.36
     вероят
    0.36
    Activations Density 0.001%

    No Known Activations