Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-65K
    4. 119
    Prev
    Next
    INDEX
    Explanations

    thinking about harm

    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_16_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
     statut
    0.60
     afer
    0.57
     eller
    0.56
     voie
    0.54
     celebrado
    0.54
    4
    0.54
     achet
    0.52
     sender
    0.51
     أو
    0.51
     bien
    0.51
    POSITIVE LOGITS
    s
    0.55
    r
    0.52
    board
    0.51
    ంది
    0.51
    on
    0.49
    決勝
    0.48
    ע
    0.47
    BYTES
    0.47
    りたい
    0.46
    provides
    0.46
    Activations Density 0.001%

    No Known Activations