© 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. 65807
    Prev
    Next
    INDEX
    Explanations

    public opinion or conflict

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

    envisions, amplifier, war, walk

    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
    ारी
    0.48
     handwriting
    0.47
    ኣ
    0.42
    lable
    0.42
     monomials
    0.42
     Российской
    0.40
    context
    0.40
    вчи
    0.40
     Ду
    0.39
     그리고
    0.39
    POSITIVE LOGITS
    ظ
    0.49
    ول
    0.48
    は
    0.48
     diffère
    0.47
    N
    0.46
     البته
    0.46
    antation
    0.46
    تون
    0.46
    ه
    0.45
    لم
    0.45
    Activations Density 0.001%

    No Known Activations