© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9617
    Prev
    Next
    INDEX
    Explanations

    that is mainly from

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

    instructions and meta-discussions about AI models, their capabilities or constraints, especially jailbreak-style prompts and references to policies or system rules.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
    ⵛ
    0.35
    ┍
    0.34
    يف
    0.33
    胍
    0.33
    ლე
    0.33
    ？](
    0.32
    ␥
    0.32
    ﺔ
    0.32
    άλ
    0.32
    ί
    0.32
    POSITIVE LOGITS
     that
    0.37
     advertisement
    0.36
     providence
    0.35
     Youtube
    0.34
     not
    0.32
     customer
    0.32
     vision
    0.32
     rod
    0.32
     time
    0.31
     It
    0.31
    Activations Density 3.103%

    No Known Activations