© 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. 152220
    Prev
    Next
    INDEX
    Explanations

    transactional phrases

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

    choice and consequence

    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
     вам
    0.52
    ಋ
    0.47
     миллиар
    0.46
    вут
    0.46
     descriptors
    0.45
    睪
    0.45
     illnesses
    0.44
    に加え
    0.43
    М
    0.43
    pseudo
    0.43
    POSITIVE LOGITS
     ঐতিহ্য
    0.46
    jo
    0.45
     전통
    0.45
     तत्कालीन
    0.45
    deh
    0.44
     entreprene
    0.43
    lever
    0.42
     Brest
    0.42
     sekret
    0.42
     súčas
    0.42
    Activations Density 0.001%

    No Known Activations