© 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. 194388
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    not followed by punctuation or specific words

    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
    S
    0.55
    İN
    0.49
    稳定的
    0.48
    ті
    0.46
    넋
    0.46
    ān
    0.45
    вропей
    0.45
    બ
    0.44
    賓
    0.44
    리
    0.44
    POSITIVE LOGITS
     fights
    0.54
     contests
    0.54
     hearings
    0.54
     memberships
    0.54
     qualifiers
    0.54
     kayaks
    0.53
     appels
    0.52
     hampers
    0.52
     charters
    0.51
     entries
    0.51
    Activations Density 0.001%

    No Known Activations