© 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. 14812
    Prev
    Next
    INDEX
    Explanations

    safety, security, threats, dangers

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

    safety, security, and guarantees

    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
     الحاله
    0.41
    AccessToken
    0.41
    èque
    0.40
    Equipment
    0.39
     inutil
    0.39
    并
    0.39
    新人
    0.38
     modeli
    0.38
    ওয়্যার
    0.38
    徂
    0.38
    POSITIVE LOGITS
     monitored
    0.42
     headed
    0.40
    章
    0.39
     minuto
    0.38
    CHAPTER
    0.38
     sic
    0.37
     एका
    0.36
     acted
    0.36
     violations
    0.36
     Λ
    0.36
    Activations Density 0.002%

    No Known Activations