© 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. 67706
    Prev
    Next
    INDEX
    Explanations

    social inclusion, forward users

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

    choose one or rotate

    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
     Maugin
    0.51
    ಬ್ಬಿಣ
    0.46
    篦
    0.46
     hedging
    0.46
     curator
    0.45
     स्विच
    0.44
    驄
    0.44
     प्लांट
    0.44
     psychiatrist
    0.43
     produktów
    0.43
    POSITIVE LOGITS
    u
    0.55
    ar
    0.53
    ING
    0.52
    ina
    0.51
    isso
    0.51
    ay
    0.50
    IP
    0.50
    kat
    0.50
    ovi
    0.49
    ari
    0.49
    Activations Density 0.001%

    No Known Activations