© 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. 49091
    Prev
    Next
    INDEX
    Explanations

    losses, profits, environment, mind

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

    interactive media

    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
     av
    0.48
    av
    0.43
     teatral
    0.43
     gaji
    0.43
     kv
    0.42
    ällen
    0.42
    ListPage
    0.41
     —
    0.41
    啥
    0.40
    oci
    0.40
    POSITIVE LOGITS
    廃棄
    0.51
    ೫
    0.50
     ಮಾತ್ರ
    0.50
     ಎರಡು
    0.49
    artifact
    0.49
     નક્કી
    0.49
     আবশ্যক
    0.48
     radiating
    0.48
    fifth
    0.48
    ectomy
    0.47
    Activations Density 0.000%

    No Known Activations