© 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. 105918
    Prev
    Next
    INDEX
    Explanations

    legalized until, discretion, North, loves Leah

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

    restructured text, revised passages

    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
     Huber
    0.51
     各
    0.50
     Mitarbeit
    0.49
     імені
    0.48
    嗲
    0.48
    同事
    0.47
    開幕
    0.46
     เศษ
    0.46
     ValueError
    0.45
     Staff
    0.45
    POSITIVE LOGITS
     generic
    0.50
     cyberspace
    0.44
     znacznie
    0.43
    鲷
    0.43
     comercio
    0.43
     portátil
    0.42
     usado
    0.42
     illusion
    0.41
     phenomena
    0.41
     whispers
    0.41
    Activations Density 0.000%

    No Known Activations