© 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. 12377
    Prev
    Next
    INDEX
    Explanations

    listing options or alternatives

    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
     Σ
    0.68
    Τ
    0.63
    𝐸
    0.63
     Τ
    0.62
    Эк
    0.62
    Ε
    0.62
    _|
    0.60
    Ψ
    0.60
    =>$
    0.59
    κ
    0.59
    POSITIVE LOGITS
     entendeu
    0.85
     referrals
    0.85
     descriptions
    0.82
     "%
    0.79
     limitations
    0.79
     whatever
    0.79
     ″
    0.79
     combinations
    0.76
     descriptors
    0.75
     explanations
    0.75
    Activations Density 0.252%

    No Known Activations