© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46551
    Prev
    Next
    INDEX
    Explanations

    stuck, materials, code

    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
    Autres
    0.46
    Religion
    0.45
    jería
    0.44
    炲
    0.42
     從
    0.42
    religion
    0.42
     Religion
    0.41
     egyéb
    0.41
    ."))
    0.41
     affirm
    0.40
    POSITIVE LOGITS
    oplast
    0.42
    ™
    0.41
    ™,
    0.40
     e
    0.39
     vap
    0.39
    せて
    0.38
     چی
    0.38
    潰
    0.38
     س
    0.37
     تا
    0.37
    Activations Density 0.000%

    No Known Activations