© 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. 182814
    Prev
    Next
    INDEX
    Explanations

    foreign language content

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

    conditional phrases and confirming 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
     autoridades
    0.49
    cantidad
    0.48
     restricciones
    0.47
    )
    0.47
    portion
    0.45
    ang
    0.44
     taxe
    0.44
    an
    0.42
     mercanc
    0.42
     limitado
    0.42
    POSITIVE LOGITS
     διαφορε
    0.44
    ochlor
    0.42
    மன்ற
    0.41
     ውስጥ
    0.40
    內容
    0.40
    ㅉ
    0.40
     göt
    0.40
    ymi
    0.39
    λλην
    0.39
    ではありません
    0.39
    Activations Density 0.002%

    No Known Activations