© 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. 1802
    Prev
    Next
    INDEX
    Explanations

    Imagine you are

    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
    ά
    0.30
    ależ
    0.29
    腟
    0.28
    abil
    0.28
    abili
    0.27
    ablo
    0.27
    abortion
    0.27
    أل
    0.27
    <0x82>
    0.26
    相談
    0.26
    POSITIVE LOGITS
     bip
    0.26
     entries
    0.25
     climax
    0.25
     transforms
    0.24
     withered
    0.23
     gamma
    0.22
     Eint
    0.22
     create
    0.22
     (
    0.22
     glist
    0.22
    Activations Density 0.011%

    No Known Activations