© 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. 198398
    Prev
    Next
    INDEX
    Explanations

    verifiedamovieanyvictimsmadetheseyears

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

    chain reaction process

    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
    4
    0.63
    en
    0.62
    ure
    0.61
     UR
    0.59
    2
    0.59
     US
    0.58
    ar
    0.57
    ia
    0.57
    in
    0.57
    rd
    0.57
    POSITIVE LOGITS
     edificio
    0.55
     motores
    0.51
     dipolar
    0.51
     constantes
    0.50
     unstoppable
    0.50
     grizz
    0.50
     evento
    0.50
     carico
    0.49
     costante
    0.49
     painfully
    0.49
    Activations Density 0.001%

    No Known Activations