© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4750
    Prev
    Next
    INDEX
    Explanations

    gentle and soft description

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

    gentle, quiet, soft sensory descriptions

    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_53_width_65k_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
    醜
    0.77
     ugly
    0.76
     disgusting
    0.73
     aggressive
    0.71
     horrendous
    0.69
     nasty
    0.68
    丑
    0.68
    狠
    0.68
    🤬
    0.68
     brutal
    0.68
    POSITIVE LOGITS
     gently
    1.56
     softly
    1.52
     gentle
    1.50
     Gentle
    1.38
     Gently
    1.37
     softness
    1.30
     soothing
    1.23
     lembut
    1.23
     delicately
    1.22
     delicate
    1.21
    Activations Density 0.319%

    No Known Activations