© 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. 5816
    Prev
    Next
    INDEX
    Explanations

    places and names

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

    code block opening braces

    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
     personalised
    0.50
     '
    0.46
     {
    0.43
     characterised
    0.42
     standardised
    0.41
    坝
    0.41
     miracle
    0.40
     barriers
    0.40
     globalisation
    0.40
    য়া
    0.39
    POSITIVE LOGITS
    Dont
    0.50
    mAvailable
    0.49
    گفت
    0.46
    dont
    0.45
    ;}
    0.44
     さらに
    0.43
    ?}
    0.42
     doesnt
    0.42
    more
    0.42
    }{}
    0.42
    Activations Density 0.000%

    No Known Activations