© 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. 29944
    Prev
    Next
    INDEX
    Explanations

    form factor, rituals, experience, password, blind

    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
    echen
    0.47
     Ц
    0.45
     langfrist
    0.43
     conjugacy
    0.42
     fart
    0.42
     گوگل
    0.41
    bilical
    0.41
     Pfe
    0.40
    .[[
    0.40
    𝐶
    0.40
    POSITIVE LOGITS
    τό
    0.45
    єд
    0.42
     couldn
    0.41
    mybatis
    0.40
    执行
    0.39
     empê
    0.39
    τία
    0.39
     dreaded
    0.38
     defies
    0.37
    这意味着
    0.37
    Activations Density 0.015%

    No Known Activations