© 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. 112440
    Prev
    Next
    INDEX
    Explanations

    seek and change what

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

    getting comprehensive information

    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
    ższ
    0.54
    h
    0.48
    SignUp
    0.48
     окре
    0.45
    i
    0.44
    зни
    0.44
    general
    0.43
    innov
    0.43
    asiti
    0.43
    렜
    0.42
    POSITIVE LOGITS
     batalha
    0.48
    נג
    0.45
    ]$,
    0.45
     webcam
    0.44
     crucifixion
    0.44
     dolphin
    0.42
    ]^{+}$
    0.42
    াত
    0.42
     tumeur
    0.41
    িস্টার
    0.41
    Activations Density 0.000%

    No Known Activations