© 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. 138120
    Prev
    Next
    INDEX
    Explanations

    commerce and legal judgments

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

    fragile promise and vulnerable aspects

    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
    幹
    0.53
    стави
    0.50
    бор
    0.48
    пусти
    0.48
     couches
    0.48
    𝗽
    0.47
     গা
    0.47
    зах
    0.46
    ণাস্ত্র
    0.46
    價
    0.46
    POSITIVE LOGITS
    ral
    0.48
    xe
    0.48
    mera
    0.46
    5
    0.46
     સામાન્ય
    0.45
    iam
    0.45
     Q
    0.44
     konflik
    0.44
     demise
    0.44
    ett
    0.43
    Activations Density 0.000%

    No Known Activations