© 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. 25396
    Prev
    Next
    INDEX
    Explanations

    specific phrases and following words

    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
    Ꭿ
    0.47
     courteous
    0.46
     pornography
    0.46
     வித்திய
    0.45
     consentimiento
    0.44
    𝐳
    0.43
    словия
    0.43
    𝒸
    0.43
    律师
    0.42
    송
    0.42
    POSITIVE LOGITS
     capable
    0.50
     geometry
    0.47
     ductile
    0.43
     capaces
    0.42
     axially
    0.42
     intrins
    0.41
     NN
    0.41
     capables
    0.40
     দৈর্ঘ
    0.40
     geometrically
    0.40
    Activations Density 0.001%

    No Known Activations