© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 10078
    Prev
    Next
    INDEX
    Explanations

    sexual assault and addiction resources

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

    Finds mentions of crisis support resources and helplines (references to hotlines, emergency contact info, or organizations offering help).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     the
    0.43
     have
    0.38
    ,
    0.38
     even
    0.36
     The
    0.33
     more
    0.32
     its
    0.32
    .
    0.31
     margin
    0.31
     appunto
    0.31
    POSITIVE LOGITS
    ༡
    0.39
    喜剧
    0.38
     сексуа
    0.38
     школе
    0.37
    预防
    0.37
    <unused730>
    0.36
    <unused698>
    0.36
    <unused1068>
    0.35
     книга
    0.35
    ૩
    0.35
    Activations Density 0.273%

    No Known Activations