© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 658
    Prev
    Next
    INDEX
    Explanations

    speaking in the world

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

    coding knowledge

    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_53_width_65k_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
    ঘ্রই
    0.21
     పాటు
    0.20
     জনপ্রিয়
    0.19
    ួល
    0.19
    ]}$.
    0.19
     jumpa
    0.19
    ಟ್
    0.19
     బ్రిటి
    0.19
     ಮಾಡಲು
    0.19
     pestaña
    0.19
    POSITIVE LOGITS
     despite
    0.37
    ––
    0.36
     —
    0.35
    —
    0.35
    despite
    0.34
     insofar
    0.33
     inasmuch
    0.33
    —-
    0.33
     несмотря
    0.32
    —“
    0.29
    Activations Density 10.493%

    No Known Activations