© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91334
    Prev
    Next
    INDEX
    Explanations

    safety/description of negative qualities

    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_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
    क्ल
    0.52
    宣传
    0.49
    campaign
    0.49
    Estas
    0.48
    astaan
    0.48
    attività
    0.47
    btnUn
    0.47
    傃
    0.46
    pèce
    0.45
     అక్క
    0.44
    POSITIVE LOGITS
    ,
    0.55
     trong
    0.54
     variables
    0.50
     scholars
    0.48
     boolean
    0.44
     analysts
    0.44
     currents
    0.43
     probabilistic
    0.42
     piecewise
    0.41
     t
    0.40
    Activations Density 0.003%

    No Known Activations