© 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. 244659
    Prev
    Next
    INDEX
    Explanations

    fill the reuseable filter

    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
    ra
    0.51
    )'
    0.49
    er
    0.47
    JACK
    0.47
    嗘
    0.45
    ],
    0.45
    jack
    0.45
    ]'
    0.44
    setosa
    0.44
    a
    0.43
    POSITIVE LOGITS
     будь
    0.57
     fikir
    0.57
     koy
    0.53
     iyong
    0.52
     ниж
    0.51
     güven
    0.51
     المع
    0.49
     креди
    0.49
     sizin
    0.49
     ভাগে
    0.49
    Activations Density 0.000%

    No Known Activations