© 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. 56090
    Prev
    Next
    INDEX
    Explanations

    into her

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

    subtly describe intellectual constitution

    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
    toRadians
    0.47
     网
    0.47
    ান্তি
    0.45
     Complaints
    0.43
     boldly
    0.43
     완료
    0.43
     waterfalls
    0.42
     Coal
    0.42
     Acceleration
    0.42
    ("""
    0.41
    POSITIVE LOGITS
    憲
    0.49
     intellect
    0.48
    攣
    0.46
    yas
    0.46
    intel
    0.45
    constitution
    0.44
     основных
    0.44
    ຢູ່ໃນ
    0.44
     воспомина
    0.44
     интеллек
    0.44
    Activations Density 0.000%

    No Known Activations