© 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. 31159
    Prev
    Next
    INDEX
    Explanations

    biblical verse number 4

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

    multiline | thinking

    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
     rownames
    0.44
    ಾಗಿತ್ತು
    0.44
    icosia
    0.43
     changeset
    0.42
     saddo
    0.41
    rownames
    0.40
     thisobject
    0.40
    ខ
    0.40
    lobby
    0.39
     uname
    0.38
    POSITIVE LOGITS
     independência
    0.46
     Munro
    0.45
     характера
    0.45
     autres
    0.43
     Müller
    0.43
     Intellectual
    0.43
     BPA
    0.43
     Pritchard
    0.43
     Energies
    0.43
     মিডিয়ায়
    0.42
    Activations Density 0.001%

    No Known Activations