© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3117
    Prev
    Next
    INDEX
    Explanations

    identifying inappropriate content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Fix
    1.09
     fixes
    1.03
     Cont
    1.02
     Res
    1.02
     Rel
    1.01
     fix
    0.97
    局
    0.93
     Re
    0.88
     Resid
    0.87
     Br
    0.84
    POSITIVE LOGITS
    genuine
    1.55
    personalized
    1.40
     выбран
    1.36
    desired
    1.34
     fútbol
    1.32
    specified
    1.31
     socalled
    1.30
     fermionic
    1.30
     darker
    1.29
    <unused2221>
    1.28
    Activations Density 0.071%

    No Known Activations