© 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. 234146
    Prev
    Next
    INDEX
    Explanations

    networking sites

    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
    Nä
    0.51
    })+
    0.46
    För
    0.44
    Donate
    0.43
    gives
    0.43
     countenance
    0.43
     fortæ
    0.43
    谶
    0.42
     avanzar
    0.42
    Tell
    0.42
    POSITIVE LOGITS
     SOME
    0.56
    されている
    0.52
    その他の
    0.48
    服務
    0.47
    島の
    0.47
    льные
    0.46
     τῶν
    0.46
     Київ
    0.46
    煎
    0.46
     большинства
    0.46
    Activations Density 0.000%

    No Known Activations