© 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. 69641
    Prev
    Next
    INDEX
    Explanations

    real estate and investment opportunities

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

    specialized information contexts. information, context, entities, actions

    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
    ADESH
    0.44
     bytecode
    0.43
     சுவர்
    0.43
     gorge
    0.43
    出行
    0.42
    OLOGIA
    0.41
     円
    0.40
    ITAL
    0.40
    扬
    0.39
    Շ
    0.39
    POSITIVE LOGITS
     Custom
    0.49
     писал
    0.46
    atory
    0.45
     Inquiry
    0.44
     informing
    0.44
    ales
    0.44
     Post
    0.44
     Informations
    0.44
     Supernatural
    0.43
     Remington
    0.42
    Activations Density 0.000%

    No Known Activations