© 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. 194693
    Prev
    Next
    INDEX
    Explanations

    research and analysis

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

    Long "} {'Locked': 'Gate', 'time': 'machine', 'sound': 'like', 'Traffic': ':'

    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
    ாட்ட
    0.43
    สำหรับ
    0.43
    э
    0.42
    కర్
    0.42
    έ
    0.41
    Gameplay
    0.41
    playable
    0.41
    𝒊
    0.41
     услуг
    0.40
     डाली
    0.40
    POSITIVE LOGITS
     Boko
    0.47
     lezen
    0.46
     indonesia
    0.43
    frica
    0.43
     Archipelago
    0.43
     archipelago
    0.42
    lo
    0.42
    komen
    0.42
     dogged
    0.41
     могла
    0.41
    Activations Density 0.000%

    No Known Activations