© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6320
    Prev
    Next
    INDEX
    Explanations

    how to instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     pots
    0.66
     விவர
    0.65
     rzeczyw
    0.64
     δεδο
    0.63
     --
    0.63
     ít
    0.62
    uc
    0.61
     databases
    0.61
     -
    0.59
     ठोस
    0.59
    POSITIVE LOGITS
     wajib
    0.84
    Remember
    0.74
     perfetta
    0.72
    如何在
    0.72
     този
    0.71
    TimeTo
    0.69
     optional
    0.69
     ഈ
    0.69
    тип
    0.69
    使い方
    0.68
    Activations Density 0.030%

    No Known Activations