Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13386
    Prev
    Next
    INDEX
    Explanations

    Abuse & Incest National Network

    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_16k_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
    ICH
    0.35
    def
    0.35
    ang
    0.34
    service
    0.34
    WIS
    0.33
    CH
    0.32
    ân
    0.32
    а
    0.32
    CA
    0.32
    national
    0.32
    POSITIVE LOGITS
     dreamy
    0.39
     wreak
    0.39
     baddies
    0.37
     gemüt
    0.37
     smelly
    0.37
     sadistic
    0.36
     Oogie
    0.35
     ආකාර
    0.35
     grungy
    0.35
     👀
    0.35
    Activations Density 0.052%

    No Known Activations