© 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. 57324
    Prev
    Next
    INDEX
    Explanations

    replies per

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

    interpreting or selecting specific information

    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
    θ
    0.47
    ভূমি
    0.45
    Ж
    0.45
    Y
    0.45
    MPI
    0.45
    θέ
    0.44
    сима
    0.43
     жү
    0.42
    EPA
    0.42
    N
    0.42
    POSITIVE LOGITS
     росій
    0.50
    と同じ
    0.48
    がいい
    0.44
     obedient
    0.42
    irió
    0.42
    cellaneous
    0.41
    に適
    0.41
     რომელი
    0.41
     電
    0.40
     injuring
    0.40
    Activations Density 0.000%

    No Known Activations