© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8368
    Prev
    Next
    INDEX
    Explanations

    youtube links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
    （
    1.52
     (
    1.49
     }}(
    1.46
    }(
    1.38
    এ
    1.35
     }(
    1.34
     (,
    1.32
     }}(\
    1.32
     （
    1.31
     (.
    1.29
    POSITIVE LOGITS
     despite
    1.50
     رغم
    1.42
     spite
    1.35
     제가
    1.20
     nonostante
    1.20
     even
    1.15
     meski
    1.11
     meskipun
    1.11
     Meskipun
    1.08
     walaupun
    1.08
    Activations Density 0.110%

    No Known Activations