© 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. 60894
    Prev
    Next
    INDEX
    Explanations

    names and instructions

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

    reasons why even

    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
    鉚
    0.47
     القناه
    0.45
    বধূ
    0.44
    钴
    0.43
    篾
    0.43
    ו
    0.42
    .–
    0.42
    ποί
    0.42
    ຸ
    0.41
    posaż
    0.41
    POSITIVE LOGITS
    s
    0.48
     सॉरी
    0.48
     \
    0.47
     tiredness
    0.47
     psychosis
    0.46
     inability
    0.45
     International
    0.45
    attribution
    0.44
    itation
    0.44
    r
    0.43
    Activations Density 0.000%

    No Known Activations