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. 31-GEMMASCOPE-2-RES-65K
    4. 56556
    Prev
    Next
    INDEX
    Explanations

    how to / where they / CD

    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
     Academy
    0.17
     powerhouse
    0.16
     North
    0.16
     Theatre
    0.15
     Sports
    0.15
     Technology
    0.15
     Studio
    0.15
    &
    0.14
     School
    0.14
     America
    0.14
    POSITIVE LOGITS
     deleterious
    0.18
     ignor
    0.17
     trivially
    0.17
     pernicious
    0.17
     perceptible
    0.17
     excitatory
    0.17
     probl
    0.17
     ಅಂಶ
    0.17
     ignorant
    0.16
     similit
    0.16
    Activations Density 0.000%

    No Known Activations