© 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. 190654
    Prev
    Next
    INDEX
    Explanations

    n points, only, difficult or, them?, with each, itself

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

    Political Instability & Governance Issues

    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
     biomass
    0.49
     interactive
    0.46
     બીજા
    0.46
     mamm
    0.46
     கத
    0.45
     contagious
    0.45
     ఘ
    0.45
     scooters
    0.45
     subgroup
    0.44
     நோ
    0.44
    POSITIVE LOGITS
    asp
    0.48
    us
    0.45
    ilitar
    0.45
    ll
    0.44
    ｘ
    0.42
    0.42
    Anti
    0.42
    Rocky
    0.42
    rate
    0.41
    yaml
    0.41
    Activations Density 0.001%

    No Known Activations