© 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. 12895
    Prev
    Next
    INDEX
    Explanations

    target, recipient, victims, perpetrators, sender

    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
    utzerklärung
    0.48
    ibrated
    0.47
    训练
    0.44
    生まれ
    0.43
    നങ്ങൾ
    0.43
    켜
    0.43
    ações
    0.42
    さ
    0.42
    养
    0.42
    装
    0.41
    POSITIVE LOGITS
    側の
    0.48
    টির
    0.47
    বস্ত
    0.44
     berupa
    0.44
    자의
    0.43
     targets
    0.42
     soggetti
    0.41
     vessel
    0.40
     molte
    0.39
     অনেকের
    0.39
    Activations Density 0.200%

    No Known Activations