© 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. 155578
    Prev
    Next
    INDEX
    Explanations

    from brands to activities

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

    EUV lithography checkpoints

    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
    中美
    0.51
     radiography
    0.49
     modular
    0.47
     Classroom
    0.47
     Cor
    0.45
    ],”
    0.45
     confront
    0.45
     관계
    0.45
     courtroom
    0.45
     Anatomy
    0.44
    POSITIVE LOGITS
    fallen
    0.51
    ें
    0.49
    rik
    0.49
    swell
    0.48
    atang
    0.47
     đậm
    0.46
    atly
    0.46
     compren
    0.46
    evident
    0.46
    ъ
    0.45
    Activations Density 0.000%

    No Known Activations