© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 3424
    Prev
    Next
    INDEX
    Explanations

    soft, gentle, subtle 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_53_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
     hardcore
    0.54
     funniest
    0.53
     bulldog
    0.51
     ugly
    0.49
    龇
    0.49
    Awesome
    0.48
    ugly
    0.48
    鍘
    0.48
     annoying
    0.47
     aggressiveness
    0.47
    POSITIVE LOGITS
     delicate
    1.79
     gentle
    1.77
     ethereal
    1.77
     soft
    1.72
     softly
    1.61
     softness
    1.55
     Gentle
    1.51
     lembut
    1.51
     graceful
    1.48
     gently
    1.46
    Activations Density 0.298%

    No Known Activations