© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12101
    Prev
    Next
    INDEX
    Explanations

    technical terms and flows

    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_13_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
     θ
    1.21
     καὶ
    1.10
     │
    1.10
    έ
    1.07
     sir
    1.06
     Kā
    1.02
     adjectives
    1.00
     numerals
    0.98
    េ
    0.96
    hensive
    0.96
    POSITIVE LOGITS
     første
    1.37
     eerste
    1.35
     första
    1.25
     primeras
    1.25
     pierws
    1.25
     ersten
    1.24
     nantinya
    1.21
     dezelfde
    1.20
     ensimmä
    1.19
     awal
    1.18
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.