© 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. 131452
    Prev
    Next
    INDEX
    Explanations

    goals and difficulties

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

    phrases starting with these activating tokens

    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
     Foster
    0.47
     пациентов
    0.45
     Saves
    0.44
     Milling
    0.43
     Yaw
    0.43
    윈
    0.43
     Accord
    0.42
    Materials
    0.42
    Cand
    0.42
     cultivating
    0.41
    POSITIVE LOGITS
     berat
    0.50
     infin
    0.50
     conseille
    0.49
     aplikace
    0.48
    ί
    0.48
    lerin
    0.48
     blanca
    0.47
    angkah
    0.47
     teatro
    0.46
     submar
    0.46
    Activations Density 0.000%

    No Known Activations