© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6514
    Prev
    Next
    INDEX
    Explanations

    technical topics followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muß
    1.19
     
    1.13
    :-
    1.10
     ঃ
    1.08
    ᆢ
    1.06
     .......
    1.06
    ・・
    1.03
    
    1.01
     ……..
    1.01
     emphas
    1.00
    POSITIVE LOGITS
     굉장히
    1.40
    Alongside
    1.37
     kiddos
    1.34
     alongside
    1.30
    굉장
    1.29
     Alongside
    1.19
     —,
    1.16
     badass
    1.14
     whatnot
    1.13
     —
    1.12
    Activations Density 0.040%

    No Known Activations