© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8579
    Prev
    Next
    INDEX
    Explanations

    list of specifications

    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_9_width_262k_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
    Με
    1.60
     dint
    1.34
    Щ
    1.30
    Τα
    1.27
     pickles
    1.21
    Γ
    1.20
     Με
    1.19
    Ξ
    1.19
     bijection
    1.18
    Ж
    1.18
    POSITIVE LOGITS
     перехода
    1.10
     като
    1.08
     нео
    1.05
    лната
    1.05
     говоря
    1.05
     Subsidi
    1.03
     desenvolv
    1.02
     tumours
    1.01
     circul
    1.01
     subsidi
    1.00
    Activations Density 0.000%

    No Known Activations