© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4314
    Prev
    Next
    INDEX
    Explanations

    text related to safety concerns and risks associated with using lawn mowers.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    language-agnostic verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     streamwise
    0.28
     मदत
    0.27
     vielfält
    0.27
     كوس
    0.26
     εικό
    0.26
     స్
    0.26
     соб
    0.26
    ⵚ
    0.25
     못
    0.25
    твори
    0.25
    POSITIVE LOGITS
    0.43
    ando
    0.31
     know
    0.29
    AL
    0.28
    aka
    0.27
     of
    0.27
    bn
    0.27
     negativo
    0.26
     read
    0.26
     οποίο
    0.26
    Activations Density 0.108%

    No Known Activations