© 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. 40-GEMMASCOPE-2-RES-262K
    4. 98847
    Prev
    Next
    INDEX
    Explanations

    foreign language words and numbers

    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_40_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
    Balance
    0.40
    Commit
    0.39
     //
    0.37
     radial
    0.37
    </a>
    0.37
     Beautiful
    0.36
    isty
    0.36
     Jurisdiction
    0.36
     Reconciliation
    0.36
    Registration
    0.35
    POSITIVE LOGITS
     starter
    0.48
    starter
    0.45
     ಪ್ರಮಾಣ
    0.42
    ൩
    0.42
     Debian
    0.42
     starten
    0.42
     ಕುಟುಂಬ
    0.42
    Starter
    0.41
     enseign
    0.40
    abhavam
    0.40
    Activations Density 0.001%

    No Known Activations