© 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-262K
    7. 138740
    Prev
    Next
    INDEX
    Explanations

    despite negative

    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_262k_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
    z
    0.59
    v
    0.55
    tor
    0.52
    animity
    0.50
    don
    0.50
    t
    0.48
    jści
    0.48
     തര
    0.47
    tive
    0.47
    na
    0.47
    POSITIVE LOGITS
    蔺
    0.44
    пой
    0.41
    beds
    0.40
     vois
    0.40
     empl
    0.39
    賴
    0.39
     beds
    0.39
    त्ता
    0.39
     предпочита
    0.38
     bede
    0.38
    Activations Density 0.002%

    No Known Activations