© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9648
    Prev
    Next
    INDEX
    Explanations

    appreciative responses or descriptors

    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_9_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
    izing
    1.50
    
    1.36
     Algebras
    1.33
    胎
    1.25
    en
    1.24
    nich
    1.23
     eigenvalues
    1.19
    nM
    1.18
    łe
    1.18
    nare
    1.16
    POSITIVE LOGITS
     vicious
    1.39
    écoute
    1.27
    𝚂
    1.24
     Misalnya
    1.23
    랫
    1.23
     trở
    1.20
     equilíbrio
    1.20
     нижней
    1.19
     recru
    1.19
     tilting
    1.18
    Activations Density 0.000%

    No Known Activations