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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 198
    Prev
    Next
    INDEX
    Explanations

    confirm reservations

    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
    ers
    1.59
    __(
    1.51
    __()
    1.47
    뭉
    1.45
     ocurrido
    1.42
    ernation
    1.41
    resh
    1.40
     viewpoint
    1.36
    лід
    1.36
    idikan
    1.33
    POSITIVE LOGITS
     incorpora
    2.04
     Ornament
    2.01
     এলিট
    1.96
     ornament
    1.85
     πρά
    1.79
     Acces
    1.78
     Macros
    1.77
     Fittings
    1.77
    傚
    1.76
     Memorial
    1.74
    Activations Density 0.000%

    No Known Activations