© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108050
    Prev
    Next
    INDEX
    Explanations

    Emotional Range

    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
    ünft
    0.44
    ů
    0.44
    늙
    0.44
    ُ
    0.44
    න්
    0.42
     nombres
    0.42
     vzd
    0.42
    ě
    0.41
    母亲
    0.41
     zle
    0.40
    POSITIVE LOGITS
    AES
    0.51
    becomes
    0.49
    Displayed
    0.48
    TISE
    0.46
     EURO
    0.45
    र्फ
    0.45
    Eu
    0.45
    ्रम
    0.44
    HashMap
    0.44
     eggplant
    0.44
    Activations Density 0.000%

    No Known Activations