© 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. 150240
    Prev
    Next
    INDEX
    Explanations

    organization or event details

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

    assuming an

    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
     puertos
    0.57
     teorías
    0.56
     milhões
    0.54
     bilhões
    0.54
     británico
    0.54
    𝔱
    0.54
     millones
    0.52
     códigos
    0.49
    為
    0.49
     pertenec
    0.48
    POSITIVE LOGITS
     and
    0.53
    ad
    0.52
    ng
    0.52
     or
    0.51
     Mini
    0.49
    l
    0.49
     project
    0.48
    x
    0.48
    ion
    0.48
     Park
    0.48
    Activations Density 0.000%

    No Known Activations