© 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. 169156
    Prev
    Next
    INDEX
    Explanations

    shall not liable

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

    structured descriptive nouns

    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
     Via
    0.50
    Path
    0.46
     DID
    0.45
    Addr
    0.44
     E
    0.44
    Namespace
    0.44
     D
    0.44
     armour
    0.43
    URL
    0.42
     ISE
    0.41
    POSITIVE LOGITS
    ņu
    0.54
    ኵ
    0.54
    뻘
    0.51
    服务的
    0.49
     शकता
    0.49
    ﻙ
    0.48
    untansi
    0.48
     serviço
    0.47
     услуг
    0.47
     услуги
    0.47
    Activations Density 0.001%

    No Known Activations