© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156201
    Prev
    Next
    INDEX
    Explanations

    descriptive opinions of appearance

    np_acts-logits-general · gemini-2.5-flash-lite

    forest OR bosque noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     although
    0.47
    竟
    0.44
    有望
    0.43
    幅広い
    0.43
     থাকলেও
    0.43
    たた
    0.42
     missing
    0.42
     penalized
    0.41
    有可能
    0.41
     possibili
    0.40
    POSITIVE LOGITS
     synaptic
    0.48
    Transmit
    0.47
    Intrinsic
    0.47
    ጇ
    0.46
    ضع
    0.44
    Expiry
    0.43
    腧
    0.43
     Strukturen
    0.43
    Credential
    0.42
     Transmitter
    0.42
    Activations Density 0.000%

    No Known Activations