© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 28120
    Prev
    Next
    INDEX
    Explanations

    joke, bartender, relationship

    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
    en
    0.67
    ul
    0.51
    um
    0.46
    m
    0.44
    uin
    0.44
    opically
    0.43
    án
    0.43
    ">'
    0.43
    u
    0.42
    ivate
    0.41
    POSITIVE LOGITS
     axiomatic
    0.51
    Logistic
    0.47
    gstatic
    0.46
     Государ
    0.46
     சட்டமன்ற
    0.45
    মানুষ
    0.45
    Correction
    0.45
    Rejected
    0.44
    राज्य
    0.44
     철
    0.44
    Activations Density 0.007%

    No Known Activations