© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10663
    Prev
    Next
    INDEX
    Explanations

    super (

    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_7_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
    البه
    1.58
     तथा
    1.49
    灌
    1.44
    }--
    1.42
     物
    1.42
    樓
    1.35
    தய
    1.33
     Zert
    1.30
     \&
    1.27
     ακόμη
    1.25
    POSITIVE LOGITS
     acceptable
    1.31
     purest
    1.21
    ograph
    1.19
    юза
    1.18
     polite
    1.18
    otonic
    1.17
    cosec
    1.15
    Hound
    1.15
    ombr
    1.14
    nof
    1.11
    Activations Density 0.009%

    No Known Activations