© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 166
    Prev
    Next
    INDEX
    Explanations

    Baywatch ocean lifeguard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     irritation
    0.61
     drowsiness
    0.58
     Oscillator
    0.58
    ﺔ
    0.56
     اذا
    0.56
     sedation
    0.56
    ОВ
    0.55
     fiind
    0.55
    ﻲ
    0.55
    ОР
    0.55
    POSITIVE LOGITS
    at
    0.49
    p
    0.45
    mode
    0.45
    com
    0.44
    b
    0.43
    golang
    0.42
     Amerikan
    0.40
    通用
    0.39
    versus
    0.39
    तून
    0.39
    Activations Density 1.746%

    No Known Activations