© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14743
    Prev
    Next
    INDEX
    Explanations

    planning or more

    np_acts-logits-general · gemini-2.5-flash-lite

    don't have to share

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    }$;
    0.44
    йга
    0.44
     последствия
    0.44
     progen
    0.43
     jew
    0.41
    riminal
    0.41
    的国家
    0.40
     NETWORK
    0.40
    fted
    0.40
    結晶
    0.40
    POSITIVE LOGITS
    eating
    0.51
     ):
    0.51
     उत्सा
    0.50
    singer
    0.50
    r
    0.50
    🥳
    0.49
    troop
    0.48
    OMG
    0.48
    😫
    0.47
    ową
    0.47
    Activations Density 0.001%

    No Known Activations