© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5615
    Prev
    Next
    INDEX
    Explanations

    acknowledgment or agreement

    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_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
     say
    1.20
    Say
    1.16
     saying
    1.14
     mengatakan
    1.13
     Say
    1.10
     Saying
    1.08
    说
    1.05
     said
    0.99
    說
    0.98
     says
    0.98
    POSITIVE LOGITS
     yep
    1.03
     alright
    0.99
     hmm
    0.98
     yeah
    0.97
     okay
    0.97
     wow
    0.96
     OK
    0.96
     ok
    0.94
     oh
    0.93
     surely
    0.92
    Activations Density 0.013%

    No Known Activations