© 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. 34186
    Prev
    Next
    INDEX
    Explanations

    follow you

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

    character traits, parameters, sender addresses, magical attacks

    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
     konular
    0.48
     如
    0.46
     муниципа
    0.45
    ಿತ
    0.44
     нём
    0.44
     realizzazione
    0.44
     municipalities
    0.43
     হ
    0.42
     recreational
    0.42
     использование
    0.42
    POSITIVE LOGITS
    á
    0.50
    nama
    0.46
    進化
    0.45
    چان
    0.44
    แก้ไข
    0.44
    ijing
    0.44
    you
    0.42
    shell
    0.42
    okkaido
    0.42
    واحد
    0.42
    Activations Density 0.000%

    No Known Activations