© 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. 46893
    Prev
    Next
    INDEX
    Explanations

    you will or did

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

    cluster headaches, logistic regression

    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
     on
    0.50
     into
    0.50
    ee
    0.49
     upset
    0.49
     from
    0.48
    ]},
    0.48
    controller
    0.47
     其他
    0.46
    ],
    0.44
    an
    0.44
    POSITIVE LOGITS
     hauptsächlich
    0.52
    BPACK
    0.48
    শুধু
    0.47
     quería
    0.47
     orientado
    0.46
    Brasil
    0.46
     variétés
    0.44
    鎿
    0.43
    JUST
    0.42
    Выберите
    0.42
    Activations Density 0.000%

    No Known Activations