© 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-65K
    7. 13272
    Prev
    Next
    INDEX
    Explanations

    negative input with children

    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_65k_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
     achievable
    0.51
     wollen
    0.46
     disabilities
    0.45
     PTSD
    0.43
     attainable
    0.43
    $\
    0.43
     힘
    0.43
     achieving
    0.42
     cryogenic
    0.42
     appunto
    0.42
    POSITIVE LOGITS
    Scores
    0.48
     sämt
    0.47
    财政
    0.45
     consommateurs
    0.45
     وزار
    0.44
    യാള
    0.44
     വ്യക്തി
    0.44
     serupa
    0.44
    敛
    0.43
    ホームページ
    0.42
    Activations Density 0.014%

    No Known Activations