© 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. 42828
    Prev
    Next
    INDEX
    Explanations

    least one, may also, wish to

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

    dozen variants

    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
     dnes
    0.40
    あるいは
    0.40
     overarching
    0.39
     একথা
    0.38
     Stimmung
    0.38
     믿
    0.38
     Alternatively
    0.38
     prioritise
    0.37
     большин
    0.37
     dirigente
    0.37
    POSITIVE LOGITS
    했고
    0.55
    ፦
    0.52
    一个是
    0.44
    其中包括
    0.42
    었고
    0.41
    कार्ट
    0.41
    咛
    0.40
     fichiers
    0.40
    ₂,
    0.40
    だったので
    0.40
    Activations Density 0.001%

    No Known Activations