© 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. 156532
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and statements

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

    controlling or tracking actions

    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
     procession
    0.48
     masculino
    0.46
     processions
    0.44
    {
    0.44
     pavil
    0.44
     मात
    0.44
     kou
    0.44
    KU
    0.43
     sw
    0.43
     nedenle
    0.42
    POSITIVE LOGITS
     помогают
    0.52
    َہ
    0.48
    )=$
    0.48
     aiuta
    0.48
    ඃ
    0.47
    츈
    0.47
     separately
    0.47
    니다
    0.47
    ঞ্জ
    0.46
     scritta
    0.46
    Activations Density 0.001%

    No Known Activations