© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13284
    Prev
    Next
    INDEX
    Explanations

    describing softness

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

    softness and gentle qualities

    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_31_width_262k_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
    ı
    0.52
    ını
    0.49
     empt
    0.48
     паспо
    0.48
    সভায়
    0.47
     कायद्या
    0.47
    식회사
    0.46
     concisely
    0.46
     objRequest
    0.46
    丑
    0.46
    POSITIVE LOGITS
     soft
    1.73
    Soft
    1.63
     Soft
    1.62
     softer
    1.55
    soft
    1.52
     softness
    1.51
    软
    1.48
     SOFT
    1.45
     soften
    1.42
     lembut
    1.38
    Activations Density 0.049%

    No Known Activations