© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5981
    Prev
    Next
    INDEX
    Explanations

    programming and model instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ంది
    0.51
     portent
    0.51
    μφωνα
    0.48
    Hoy
    0.46
    説
    0.45
    November
    0.44
    ዥ
    0.43
    าย
    0.43
    ுகிறது
    0.42
    倬
    0.41
    POSITIVE LOGITS
    quela
    0.59
     ragazze
    0.55
    quele
    0.51
     béton
    0.50
     attaques
    0.50
     inférieures
    0.49
     devenue
    0.49
     poitrine
    0.48
     atracción
    0.47
     películas
    0.47
    Activations Density 0.081%

    No Known Activations