© 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-262K
    4. 34984
    Prev
    Next
    INDEX
    Explanations

    but introduces a contrast

    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
    胺
    0.41
     fiche
    0.40
    து
    0.40
    terre
    0.39
    工作中
    0.38
    פר
    0.38
    रु
    0.38
    督
    0.37
    اه
    0.37
     кома
    0.37
    POSITIVE LOGITS
    をお願い
    0.40
    itabbo
    0.39
     exchanges
    0.38
     intercamb
    0.38
     regelmäßig
    0.37
    outez
    0.37
     อย่า
    0.36
    DropdownBox
    0.36
     मानसून
    0.36
    ◠
    0.36
    Activations Density 0.001%

    No Known Activations