© 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. 209191
    Prev
    Next
    INDEX
    Explanations

    locations and specific entities

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

    not suggesting persona

    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
     awful
    0.46
    TR
    0.45
     стандарт
    0.43
    の良い
    0.42
     latéraux
    0.42
     вариантов
    0.41
    샹
    0.41
    の大
    0.41
    на
    0.41
     Restrictions
    0.41
    POSITIVE LOGITS
    yesi
    0.50
     आईएएस
    0.48
    park
    0.47
     एक्चु
    0.46
     endere
    0.46
    䄱
    0.46
    rakt
    0.46
     NEET
    0.45
     quien
    0.45
     conlle
    0.45
    Activations Density 0.000%

    No Known Activations