© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27726
    Prev
    Next
    INDEX
    Explanations

    negative adjectives and judgment

    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_40_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
    🫶
    0.80
     ২০২৩
    0.73
     ২০২২
    0.73
    🥹
    0.72
    🩷
    0.71
     TikTok
    0.70
    🫣
    0.68
     🥰
    0.66
    🤎
    0.66
    🥰
    0.66
    POSITIVE LOGITS
     blatantly
    0.64
     retarded
    0.64
     crippling
    0.61
     simplistic
    0.59
     retardation
    0.56
     homosexual
    0.55
     psychotic
    0.54
     populace
    0.53
     raping
    0.52
     blatant
    0.52
    Activations Density 0.005%

    No Known Activations