© 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. 69298
    Prev
    Next
    INDEX
    Explanations

    actions and responses

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

    updates, cybernetic, appointments

    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
     हड्डी
    0.49
    厂
    0.49
     effluents
    0.49
     да
    0.48
    aties
    0.48
     explica
    0.47
     रास्ते
    0.47
     успешно
    0.47
     दर्द
    0.46
    ibilidad
    0.45
    POSITIVE LOGITS
     realist
    0.46
     Appointments
    0.46
     konfer
    0.46
    ริม
    0.44
    Appointments
    0.43
    ᓃ
    0.42
     Instruction
    0.41
     Denote
    0.40
    は約
    0.40
    ੁ
    0.40
    Activations Density 0.001%

    No Known Activations