© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 933
    Prev
    Next
    INDEX
    Explanations

    `reassess`, `perpetuating`, `decohere`, `aislar`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    torio
    1.22
     Fores
    1.19
    atorio
    1.15
     に対
    1.13
     }}(
    1.08
    事务所
    1.08
    ilogue
    1.06
    }}}{\
    1.06
    cimentos
    1.03
     adequacy
    1.03
    POSITIVE LOGITS
    켜
    1.49
     dientes
    1.42
    scrib
    1.41
    allocate
    1.41
    łożyć
    1.40
    ключа
    1.39
    lägt
    1.36
     initialize
    1.35
    introduce
    1.35
    produce
    1.33
    Activations Density 0.759%

    No Known Activations