© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 116980
    Prev
    Next
    INDEX
    Explanations

    просто followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ла
    0.86
    வ
    0.74
    owym
    0.70
     první
    0.67
    માં
    0.67
     weiterer
    0.67
    ید
    0.66
    к
    0.66
    owanym
    0.65
    ত
    0.64
    POSITIVE LOGITS
    MW
    0.59
    čka
    0.58
    ct
    0.58
    čki
    0.57
     fracking
    0.57
    italia
    0.56
    _
    0.56
    pe
    0.55
    ni
    0.55
    terus
    0.55
    Activations Density 0.001%

    No Known Activations