© 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. 11017
    Prev
    Next
    INDEX
    Explanations

    indicating trouble

    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
    ]&
    1.74
    spired
    1.66
    Iddict
    1.64
    tegr
    1.63
    &(
    1.61
    স
    1.58
    &-
    1.58
     ঘোষ
    1.58
    ク
    1.51
    ddots
    1.50
    POSITIVE LOGITS
     dient
    1.30
     variétés
    1.29
     favorite
    1.27
     dio
    1.26
    ую
    1.25
    žené
    1.24
     serre
    1.23
     poden
    1.20
     reichen
    1.19
     noemen
    1.18
    Activations Density 0.008%

    No Known Activations