© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166290
    Prev
    Next
    INDEX
    Explanations

    important information or caution

    np_acts-logits-general · gemini-2.5-flash-lite

    planning and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     কিংবা
    0.46
    ម្ល
    0.45
    <tr>
    0.45
    碗
    0.44
    వారి
    0.42
    １
    0.42
    кого
    0.41
     colorless
    0.41
    専門店
    0.41
    憎
    0.40
    POSITIVE LOGITS
     সতর্কতা
    0.55
    caution
    0.51
     Emergency
    0.50
     Protección
    0.49
     গুরুত্বপূর্ণ
    0.48
     Osten
    0.47
     Basketball
    0.47
     Lesen
    0.47
     bảo
    0.46
     öst
    0.46
    Activations Density 0.000%

    No Known Activations