© 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. 175151
    Prev
    Next
    INDEX
    Explanations

    booking online or in person

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

    even though

    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
    nip
    0.47
    nT
    0.47
     humano
    0.46
    俦
    0.46
    古典
    0.45
    RL
    0.44
    ப்படுக
    0.44
     legge
    0.44
    hAP
    0.43
     Attendance
    0.43
    POSITIVE LOGITS
    수가
    0.52
    planting
    0.45
     '*',
    0.44
     🌱
    0.44
    मा
    0.43
     hydrant
    0.43
     পরই
    0.43
    บาล
    0.42
    ভান
    0.42
     surfacing
    0.42
    Activations Density 0.001%

    No Known Activations