Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41370
    Prev
    Next
    INDEX
    Explanations

    announcing future plans or decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     reported
    0.84
     refe
    0.82
     aliments
    0.80
    り
    0.78
     alanı
    0.78
     রিপোর্ট
    0.77
     doubt
    0.76
    м
    0.75
    THING
    0.74
     owed
    0.74
    POSITIVE LOGITS
     plans
    1.59
    plans
    1.57
    Plans
    1.46
     PLANS
    1.36
     Plans
    1.34
     intentions
    1.19
    intention
    1.13
     intention
    1.05
    Decision
    1.02
     планы
    0.99
    Activations Density 0.006%

    No Known Activations