© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13000
    Prev
    Next
    INDEX
    Explanations

    this followed by a word

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

    this is new

    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
    zelfde
    0.42
     подви
    0.41
    ㄽ
    0.39
    роме
    0.39
    পাতালে
    0.38
     күзгү
    0.38
    textrm
    0.38
    centred
    0.38
     	i
    0.38
    крема
    0.37
    POSITIVE LOGITS
     accusing
    0.41
     التي
    0.38
     الذي
    0.38
     myriad
    0.37
    简直
    0.37
     accusations
    0.36
     الذين
    0.36
     Emperor
    0.36
     accusation
    0.36
     uproar
    0.35
    Activations Density 0.134%

    No Known Activations