© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1183
    Prev
    Next
    INDEX
    Explanations

    maximum, default, target, base

    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_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
     famosa
    1.57
     berühm
    1.56
     rinnov
    1.48
     grandes
    1.45
    著名的
    1.44
     destac
    1.41
     famoso
    1.40
    ň
    1.39
     gigantes
    1.39
     großen
    1.39
    POSITIVE LOGITS
    IMUM
    1.72
    imum
    1.55
    temperature
    1.48
     temperature
    1.30
    ocation
    1.27
    mum
    1.27
    widths
    1.26
     altitude
    1.26
    altitude
    1.26
    tenance
    1.25
    Activations Density 0.569%

    No Known Activations