© 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. 123057
    Prev
    Next
    INDEX
    Explanations

    Indian Country, Saudi police, withdrawal from

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

    arguments and claims

    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
     sympat
    0.45
    ബ്രുവരി
    0.44
    誂
    0.43
     devising
    0.42
    issances
    0.42
    이션
    0.42
     cannibal
    0.42
     Adele
    0.42
     herunter
    0.42
    以下の
    0.41
    POSITIVE LOGITS
    uk
    0.56
    you
    0.55
    t
    0.52
    di
    0.51
    или
    0.51
    ung
    0.51
    lr
    0.50
    1
    0.49
    ll
    0.49
    truck
    0.49
    Activations Density 0.001%

    No Known Activations